© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64365
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    istr
    -0.27
    è¿Ļ个游æĪı
    -0.26
    éĤ£ä¹Īç®Ģåįķ
    -0.26
    æĥ³æ³ķ
    -0.24
    èĭĩ
    -0.24
    éĢĤåIJĪèĩªå·±
    -0.23
    å½ĵä¸Ń
    -0.23
    odo
    -0.23
    dic
    -0.23
    åī¯å±Ģéķ¿
    -0.23
    POSITIVE LOGITS
    å¯ĦãģĽ
    0.30
    ç§ijæĬĢ大åѦ
    0.28
     per
    0.27
    Unchecked
    0.27
    zet
    0.26
    纳
    0.26
    ashboard
    0.25
     Falls
    0.24
    uciones
    0.24
    *
    0.24
    Activations Density 21.257%

    No Known Activations