© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39108
    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
    Not in Any Lists

    No Comments

    Negative Logits
    家
    -0.29
    bh
    -0.26
    phis
    -0.26
    头ä¸Ĭ
    -0.26
    .tt
    -0.26
    ()._
    -0.26
    ypy
    -0.25
    æĺ¯ä»Ģä¹Īåij¢
    -0.25
    lescope
    -0.25
     Matth
    -0.25
    POSITIVE LOGITS
    袢
    0.32
    sort
    0.30
    pre
    0.29
    inate
    0.27
    orders
    0.27
     pre
    0.27
    surface
    0.27
    ologies
    0.26
    assert
    0.26
    utilities
    0.26
    Activations Density 2.833%

    No Known Activations

    This feature has no known activations.