© 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. 32-TRANSCODER-HP
    7. 43949
    Prev
    Next
    INDEX
    Explanations

    Device manufacturing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĢļ
    -0.31
    zas
    -0.28
    afil
    -0.27
    (express
    -0.27
     EXPRESS
    -0.26
    tor
    -0.25
    BEL
    -0.25
     ciaÅĤa
    -0.25
    onth
    -0.24
    ç½®
    -0.24
    POSITIVE LOGITS
    assic
    0.32
    æĿĥ
    0.28
    æķ°æį®
    0.27
    .nextInt
    0.26
    steen
    0.26
    .getDay
    0.25
     Sick
    0.25
     data
    0.24
     bubbles
    0.24
     buffered
    0.24
    Activations Density 0.010%

    No Known Activations