© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 41640
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    UI/navigation and blog-template boilerplate (headers, dates, widget labels like "Pages", "Blog Archive", "No comments", and similar sidebar/menu metadata).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    包围
    -0.07
    /dom
    -0.07
     capacitor
    -0.07
    XMLLoader
    -0.07
    %/
    -0.07
     hemisphere
    -0.07
    -TV
    -0.07
    用户提供
    -0.07
    已经在
    -0.06
     realloc
    -0.06
    POSITIVE LOGITS
    玱
    0.08
    كن
    0.06
     ALIGN
    0.06
     valore
    0.06
     retval
    0.06
     quyền
    0.06
     Boolean
    0.06
    ใด
    0.06
    Sorting
    0.06
    শ
    0.06
    Activations Density 0.263%

    No Known Activations