© 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. 112350
    Prev
    Next
    INDEX
    Explanations

    recycle

    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
    iated
    -0.28
    imately
    -0.27
    acker
    -0.26
    fir
    -0.26
    held
    -0.26
    åľ¨çº¿
    -0.26
    linger
    -0.25
    çļĦ认åı¯
    -0.25
    agus
    -0.25
     acknow
    -0.25
    POSITIVE LOGITS
    /rec
    0.29
    rowad
    0.27
    able
    0.26
     controversial
    0.26
    ers
    0.26
    opyright
    0.25
    è¿«åĪĩ
    0.24
    éĻIJéĩı
    0.24
    èĥ½æºIJ
    0.24
     waste
    0.24
    Activations Density 0.101%

    No Known Activations