© 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. 40725
    Prev
    Next
    INDEX
    Explanations

    Code and special characters

    np_max-act-logits · gemini-2.0-flash
    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
    士
    -0.30
    ffects
    -0.25
    çİĭèĢħ
    -0.24
     Anniversary
    -0.24
    èĥľè´Ł
    -0.24
     bringing
    -0.24
    iente
    -0.24
    (styles
    -0.23
     beh
    -0.23
    ä¸įä¼ļæľī
    -0.23
    POSITIVE LOGITS
    ä¹ŁæŃ£æĺ¯
    0.31
    éĤ¬
    0.28
    UP
    0.28
    èĦIJ
    0.27
    (up
    0.27
    æĪĸæĺ¯
    0.26
    upp
    0.25
    .up
    0.25
    up
    0.25
    unn
    0.25
    Activations Density 1.636%

    No Known Activations