© 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. 25-TRANSCODER-HP
    7. 109435
    Prev
    Next
    INDEX
    Explanations

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    adic
    -0.28
    åįķ车
    -0.26
    asonry
    -0.26
    aval
    -0.26
    oom
    -0.26
     realism
    -0.26
    <c
    -0.25
    .tell
    -0.25
    æ»´
    -0.25
    adio
    -0.24
    POSITIVE LOGITS
    /documents
    0.25
     Lonely
    0.24
     comp
    0.23
    documents
    0.23
    Marsh
    0.23
    åľ¨å¤ĸéĿ¢
    0.23
    -Star
    0.23
    计
    0.23
     bodies
    0.23
    indr
    0.23
    Activations Density 0.971%

    No Known Activations