© 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. 20-TRANSCODER-HP
    7. 108397
    Prev
    Next
    INDEX
    Explanations

    life/survival

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Ģè¿Ķ
    -0.27
     endforeach
    -0.26
    æ¼Ķ
    -0.25
    arrant
    -0.25
    akedown
    -0.25
    èĻŀ
    -0.24
    åIJĦåĽ½
    -0.24
    æĵį
    -0.24
    åIJĦå¼ı
    -0.24
     spinner
    -0.23
    POSITIVE LOGITS
    å·¥æľŁ
    0.27
    ấp
    0.25
    lc
    0.25
    sein
    0.25
    æݳ
    0.24
    èµłéĢģ
    0.23
     december
    0.23
    Fact
    0.23
    åŤ
    0.23
    éĩijåŃĹ
    0.23
    Activations Density 14.020%

    No Known Activations