© 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. 71154
    Prev
    Next
    INDEX
    Explanations

    Spanish

    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
    ipe
    -0.07
     visualize
    -0.07
    (Photo
    -0.06
     //////////////////////////////////////////////////////////////////////////
    -0.06
    簟
    -0.06
    ᆡ
    -0.06
    瑓
    -0.06
    ｅ
    -0.06
    ️
    -0.06
     wir
    -0.06
    POSITIVE LOGITS
     Perry
    0.07
    berries
    0.07
     Rodrig
    0.07
     LCS
    0.07
    蛉
    0.07
     curing
    0.07
    _APPLICATION
    0.07
     Curve
    0.07
    Slinky
    0.06
     MODIFY
    0.06
    Activations Density 0.209%

    No Known Activations