© 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. 107061
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     spirits
    -0.29
    بعث
    -0.28
    ould
    -0.25
     ib
    -0.25
     illusions
    -0.25
     secrets
    -0.25
    _migration
    -0.25
    еÑģÑĤво
    -0.24
    ['__
    -0.24
    楼å®ĩ
    -0.24
    POSITIVE LOGITS
    unner
    0.28
    "](
    0.27
    ulnerable
    0.26
    itched
    0.26
    asser
    0.26
    ruz
    0.25
    uzzer
    0.25
    arez
    0.25
    fect
    0.25
    大éĥ¨åĪĨ
    0.24
    Activations Density 0.153%

    No Known Activations

    This feature has no known activations.