© 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. 40211
    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
     whe
    -0.29
     Houses
    -0.28
     referee
    -0.27
     SqlDataReader
    -0.27
    褶
    -0.25
    .ptr
    -0.25
     buffs
    -0.24
    Routine
    -0.24
    emode
    -0.24
    imer
    -0.24
    POSITIVE LOGITS
    udy
    0.28
    omit
    0.26
    .Par
    0.26
     propre
    0.25
    -par
    0.24
    -pill
    0.24
    party
    0.24
     fourth
    0.24
     sek
    0.24
    åľ¨æİ¥åıĹ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.