© 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. 38549
    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
     XCT
    -0.30
    åĩºèµĦ
    -0.29
    panion
    -0.27
    ingly
    -0.27
    æļĤ
    -0.25
    inha
    -0.25
    ä½ĵéĩı
    -0.25
     RequestOptions
    -0.25
    -ing
    -0.25
    inue
    -0.25
    POSITIVE LOGITS
    policy
    0.25
    æĪŁ
    0.25
    éĽĨ
    0.25
    urst
    0.25
    åIJĪçIJĨ
    0.24
    lord
    0.24
    .sax
    0.24
     Redistribution
    0.24
    arrow
    0.24
    Valid
    0.23
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.