© 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. 8511
    Prev
    Next
    INDEX
    Explanations

    deadline

    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
    نش
    -0.07
     presence
    -0.07
    xac
    -0.07
    也曾
    -0.06
    .setX
    -0.06
    affected
    -0.06
    ₌
    -0.06
     herein
    -0.06
    人群中
    -0.06
    游戏当中
    -0.06
    POSITIVE LOGITS
    䥽
    0.07
    텨
    0.07
     smoothing
    0.07
    /Graphics
    0.07
    航班
    0.07
     Geile
    0.06
     Kat
    0.06
    ammers
    0.06
    arf
    0.06
     vag
    0.06
    Activations Density 0.004%

    No Known Activations