© 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. 40551
    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
    为æĪij们
    -0.34
    æľĢåIJİä¸Ģ次
    -0.31
    è¾ķ
    -0.31
    ç»ĻæĪij们
    -0.26
    ä¿Ŀä¿®
    -0.26
    ä¸Ģå¼ł
    -0.26
    å½ĵæĪij们
    -0.25
    æĹłè®ºå¦Ĥä½ķ
    -0.24
    ç»Ļ大家
    -0.24
    ).(
    -0.24
    POSITIVE LOGITS
    ora
    0.26
    pace
    0.24
    space
    0.24
     ÐĴладим
    0.24
     confines
    0.24
    witch
    0.24
    ç»Ĩå¿ĥ
    0.24
    plit
    0.23
    å®īåİ¿
    0.23
     trace
    0.23
    Activations Density 2.767%

    No Known Activations

    This feature has no known activations.