© 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. 38574
    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
    äº®çľ¼
    -0.28
    rippling
    -0.27
    ingu
    -0.26
    wa
    -0.26
     Wa
    -0.25
     starving
    -0.25
     drawer
    -0.25
    å¼Ģå¹ķ
    -0.25
    以å¾Į
    -0.25
    åģļä¸įåĪ°
    -0.24
    POSITIVE LOGITS
     Äijá»ķi
    0.25
    	DECLARE
    0.24
    arel
    0.24
    ạy
    0.24
    强
    0.24
     modifiers
    0.24
    æ²Ļ
    0.24
    éĿŀ
    0.24
     danmark
    0.23
    ç¨ĭ
    0.23
    Activations Density 0.844%

    No Known Activations

    This feature has no known activations.