© 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. 38780
    Prev
    Next
    INDEX
    Explanations

    see

    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
    å¦Ĥæŀľ
    -1.09
    if
    -0.95
     if
    -0.93
    If
    -0.90
     If
    -0.81
    èĭ¥
    -0.81
     å¦Ĥæŀľ
    -0.81
    _if
    -0.78
    -if
    -0.78
    å¦Ĥæŀľæľī
    -0.78
    POSITIVE LOGITS
    ä½Ĩ她
    0.28
    ç¡®å®ŀæĺ¯
    0.26
    ä»ĸ们æĺ¯
    0.25
    å¹²éĥ¨éĺŁä¼į
    0.23
    åİŁæĿ¥æĺ¯
    0.23
    æĪij们就
    0.23
    çļĦç¡®æĺ¯
    0.23
    èĢħãģĮ
    0.23
    她æĺ¯
    0.23
    ä½ĨæĪij们
    0.22
    Activations Density 5.170%

    No Known Activations