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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 70970
    Prev
    Next
    INDEX
    Explanations

    Bus

    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
    �
    -0.07
     Hearts
    -0.07
     argent
    -0.07
    elsius
    -0.07
    🧤
    -0.07
    刘备
    -0.07
     winnings
    -0.07
     letters
    -0.06
     toc
    -0.06
     accord
    -0.06
    POSITIVE LOGITS
     )
    0.07
    }/>↵
    0.07
    _real
    0.07
    独家
    0.07
    校长
    0.07
     bus
    0.07
    灾难
    0.07
    :def
    0.06
    _linux
    0.06
    >".
    0.06
    Activations Density 0.035%

    No Known Activations