© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 9289
    Prev
    Next
    INDEX
    Explanations

    spring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prosecuted
    -0.08
     fraction
    -0.07
    _declaration
    -0.07
    켜
    -0.07
     newValue
    -0.07
     bonds
    -0.07
     فلا
    -0.07
     קוד
    -0.07
    冲动
    -0.07
    Gratis
    -0.07
    POSITIVE LOGITS
     lucrative
    0.07
    �
    0.07
     RBI
    0.07
    ន
    0.07
     Zuk
    0.06
    LIKE
    0.06
     Returning
    0.06
     AR
    0.06
    _resolve
    0.06
    struments
    0.06
    Activations Density 0.211%

    No Known Activations