© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19593
    Prev
    Next
    INDEX
    Explanations

    blue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reeze
    -0.34
    ISTR
    -0.28
    OUNCE
    -0.28
    æ¯Ľ
    -0.26
    lek
    -0.26
    slick
    -0.26
    pike
    -0.25
    ÑĢажа
    -0.25
    _PIPELINE
    -0.25
    STRUCTION
    -0.24
    POSITIVE LOGITS
    ades
    0.30
    ãĤ³ãĥ³
    0.26
    tro
    0.25
    éĤ´
    0.25
    éĢ¢
    0.25
    idot
    0.24
    dev
    0.24
    NODE
    0.24
    ãģ¬
    0.24
     deco
    0.24
    Activations Density 0.011%

    No Known Activations