© 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. 8481
    Prev
    Next
    INDEX
    Explanations

    Chemistry and Polymers

    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
    性命
    -0.08
     amusement
    -0.07
    급
    -0.07
    ewis
    -0.07
    引力
    -0.07
    Luck
    -0.07
     בחשבון
    -0.07
    答案
    -0.07
     liberation
    -0.06
     financier
    -0.06
    POSITIVE LOGITS
    _NEED
    0.07
    𝒟
    0.07
     Nora
    0.07
    .getProduct
    0.07
    稳步
    0.07
     MUT
    0.07
    ドイ
    0.07
     Gór
    0.07
     الدر
    0.07
    Número
    0.07
    Activations Density 0.087%

    No Known Activations