© 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. 39135
    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
    èŀĥèŁ¹
    -0.24
    otomy
    -0.24
     Dudley
    -0.24
    unfold
    -0.24
    åįļè§Ī
    -0.23
    ç«ł
    -0.23
    illac
    -0.23
    ancies
    -0.23
    ants
    -0.23
     bá»ĭ
    -0.23
    POSITIVE LOGITS
    æ°´æºIJ
    0.28
    ä½ĵåĨħ
    0.25
     Graham
    0.25
     cname
    0.25
    __[
    0.24
    TN
    0.23
    诡
    0.23
    caster
    0.23
    visible
    0.23
    .Pin
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.