© 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. 40766
    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
    åħ¨çIJĥæľĢ大
    -0.29
    åĪ¶åĵģ
    -0.28
    olicited
    -0.25
    ä¸ĢæľŁ
    -0.25
    ensation
    -0.24
    perm
    -0.24
    åįĬæľĪ
    -0.24
    petition
    -0.23
    çĶ¸
    -0.23
    .mime
    -0.23
    POSITIVE LOGITS
     confirmation
    0.25
    iples
    0.25
    itis
    0.25
     jail
    0.25
    Sparse
    0.24
     confirm
    0.24
    idar
    0.24
    'O
    0.24
    cott
    0.23
    answers
    0.23
    Activations Density 0.449%

    No Known Activations

    This feature has no known activations.