© 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. 38688
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
    expires
    -0.28
    AttributeValue
    -0.24
     Yue
    -0.24
    夹
    -0.24
     doPost
    -0.23
    æ·¡åĮĸ
    -0.23
    æĪijä»¬çŁ¥éģĵ
    -0.23
     íķĺ
    -0.23
    ähl
    -0.23
    æ¡ĵ
    -0.23
    POSITIVE LOGITS
     shopper
    0.32
     boxer
    0.31
     gunman
    0.30
     gymn
    0.29
     Gamer
    0.28
     snakes
    0.28
     familiar
    0.28
     adventurer
    0.28
    STR
    0.28
     spooky
    0.28
    Activations Density 2.766%

    No Known Activations