© 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. 40598
    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
     Mayer
    -0.24
    诱导
    -0.24
     MATERIAL
    -0.24
     meters
    -0.24
    nes
    -0.24
    äºı
    -0.23
    é¦Ĭ
    -0.23
     busted
    -0.23
     conjug
    -0.23
    æķ´ä¸ªäºº
    -0.23
    POSITIVE LOGITS
    rÃŃ
    0.29
    æĬķ票
    0.26
    åIJij
    0.25
    è·³åĩº
    0.25
    onia
    0.24
     vr
    0.24
     eagerly
    0.24
    onym
    0.24
    į
    0.24
    isle
    0.24
    Activations Density 10.941%

    No Known Activations

    This feature has no known activations.