© 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. 35-TRANSCODER-HP
    7. 38748
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    allet
    -0.28
    azaar
    -0.27
    -yyyy
    -0.27
    vertising
    -0.27
    klä
    -0.26
    croft
    -0.26
    azen
    -0.26
    terminated
    -0.26
    tica
    -0.26
    locator
    -0.26
    POSITIVE LOGITS
    let
    0.29
    0.27
    d
    0.26
    uff
    0.26
    主导
    0.25
    äº§åľ°
    0.25
    (d
    0.25
    éºĤ
    0.25
    T
    0.25
    _
    0.24
    Activations Density 7.960%

    No Known Activations

    This feature has no known activations.