© 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. 38826
    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
    碣
    -0.26
    Screens
    -0.26
    ãģĦãģ¾ãģĽãĤĵ
    -0.25
    åıī
    -0.25
    å¥ij约
    -0.25
    é¢ĦåijĬ
    -0.25
    æŶæĬ¥
    -0.24
    æ¦Ĥ
    -0.24
    CHED
    -0.24
    egis
    -0.24
    POSITIVE LOGITS
    apa
    0.27
    追究
    0.27
    cai
    0.26
     instructions
    0.26
    hee
    0.26
    amac
    0.26
     criteria
    0.25
    immer
    0.25
    haar
    0.25
     MAC
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.