© 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. 87219
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    :\/\/
    -0.26
     caps
    -0.25
    éģ¿åħį
    -0.25
    agt
    -0.23
    stag
    -0.23
    _MAG
    -0.23
    shadow
    -0.23
    gre
    -0.23
    [:,:
    -0.23
    ARI
    -0.23
    POSITIVE LOGITS
    ibilidad
    0.28
    ä¸Ģ个æĸ°çļĦ
    0.26
     Mut
    0.26
    ä¸Ģ个æĺ¯
    0.26
    æĢ»ç»ĵ
    0.25
    ×Ļ×¢×Ķ
    0.25
    iber
    0.24
    reten
    0.24
    ä¼ģä¸ļåĴĮ
    0.24
    pection
    0.23
    Activations Density 0.012%

    No Known Activations