© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 87231
    Prev
    Next
    INDEX
    Explanations

    legal documents, attacks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ļ
    -0.28
    çļĦæł·åŃIJ
    -0.26
    çļĦåŁºç¡Ģ
    -0.24
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.24
    [:]
    -0.24
    å°±æĺ¯è¿Ļæł·
    -0.23
     viz
    -0.23
    .asInstanceOf
    -0.23
    çļĦæĥħå½¢
    -0.23
     Verfügung
    -0.23
    POSITIVE LOGITS
    ographically
    0.29
    ichern
    0.26
    UPS
    0.26
    -bal
    0.25
     Hawth
    0.24
    rä
    0.24
    uju
    0.24
    ewhere
    0.24
    azers
    0.24
    ously
    0.24
    Activations Density 0.002%

    No Known Activations