© 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. 44886
    Prev
    Next
    INDEX
    Explanations

    quotation marks/colons

    np_max-act · gemini-2.0-flash
    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
     LinkedHashMap
    -0.07
     gamm
    -0.07
     themselves
    -0.07
     communic
    -0.07
    Ꮠ
    -0.07
    Fear
    -0.07
     Mexico
    -0.07
    _CBC
    -0.06
    汲
    -0.06
    enco
    -0.06
    POSITIVE LOGITS
     Reflect
    0.08
     tops
    0.07
    ;*/↵
    0.07
    folios
    0.07
     неделю
    0.07
    iel
    0.07
    ").↵
    0.07
    	initial
    0.07
    orld
    0.06
    近日
    0.06
    Activations Density 0.035%

    No Known Activations