© 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. 40542
    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
     Toy
    -0.26
     accused
    -0.26
    ework
    -0.25
    è¿ĺä¸įå¦Ĥ
    -0.25
    arkin
    -0.24
     sino
    -0.24
    çĬ¯
    -0.23
     Inst
    -0.23
    æĮĩ示
    -0.23
    inea
    -0.23
    POSITIVE LOGITS
    åĽŀæĶ¶
    0.28
    erce
    0.27
    æĬij
    0.25
    æĪĸèĢħåħ¶ä»ĸ
    0.25
    izard
    0.24
    æĶ¶åĽŀ
    0.24
    è¿Ł
    0.23
    exterity
    0.23
    ez
    0.23
    INavigation
    0.23
    Activations Density 0.782%

    No Known Activations

    This feature has no known activations.