© 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. 107177
    Prev
    Next
    INDEX
    Explanations

    Holidays

    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
    @section
    -0.28
    deps
    -0.27
    nia
    -0.27
    /MIT
    -0.26
     moderators
    -0.26
    çĶ¨æĪ·æıIJä¾Ľ
    -0.26
     Chall
    -0.26
    Toast
    -0.25
    clid
    -0.25
    Enc
    -0.25
    POSITIVE LOGITS
     multic
    0.35
    util
    0.30
    ä¸įè¿ľ
    0.29
    ofi
    0.27
     groundwater
    0.26
    afa
    0.25
    æ²³æµģ
    0.25
    isplay
    0.25
    TypeID
    0.25
     scour
    0.25
    Activations Density 0.898%

    No Known Activations