© 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. 40739
    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
     squads
    -0.30
     demos
    -0.27
     organising
    -0.27
    acus
    -0.27
     chops
    -0.26
    mony
    -0.26
     cannons
    -0.25
    shine
    -0.25
    -pad
    -0.25
     amps
    -0.25
    POSITIVE LOGITS
    羣çĪ±
    0.30
    :
    0.30
    ,
    0.28
     und
    0.28
     is
    0.28
     has
    0.28
    æµģåĩº
    0.27
    åħ¶æīĢ
    0.27
     by
    0.27
    ;
    0.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.