© 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. 40721
    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
    ánd
    -0.29
    abin
    -0.29
    acle
    -0.28
    odings
    -0.27
    mailbox
    -0.26
    arial
    -0.25
    plate
    -0.24
     ********************************************************
    -0.24
    åĽ´
    -0.24
    /send
    -0.24
    POSITIVE LOGITS
    insk
    0.25
     MISS
    0.25
    å§Ķ
    0.24
    umba
    0.24
    åħįéĻ¤
    0.24
     Ranger
    0.24
    -UA
    0.24
    jin
    0.23
     Rae
    0.23
    -fit
    0.23
    Activations Density 50.060%

    No Known Activations

    This feature has no known activations.