© 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. 19-RESID-POST-AA
    11. 69200
    Prev
    Next
    INDEX
    Explanations

    Charles

    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
    臨
    -0.08
    鼱
    -0.07
     wee
    -0.07
    vang
    -0.07
    🤰
    -0.07
     Hôm
    -0.07
    景
    -0.07
    (private
    -0.07
    疲れ
    -0.07
    停电
    -0.07
    POSITIVE LOGITS
    字样
    0.08
     zone
    0.08
    ederation
    0.07
    สโมสร
    0.07
     cab
    0.07
    可达
    0.07
     durch
    0.07
     VER
    0.07
     regex
    0.07
     sav
    0.07
    Activations Density 0.007%

    No Known Activations