© 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. 62641
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Negative Logits
     mars
    -0.26
     Burr
    -0.26
    ìļ°
    -0.26
    å¦Ĥæľīä¾µæĿĥ
    -0.26
    ç»ĻäºĪäºĨ
    -0.25
    ä¸ĺ
    -0.24
    >t
    -0.24
    è®Ń
    -0.23
    ãĢij,
    -0.23
    åİŁæĸĩåľ°åĿĢ
    -0.23
    POSITIVE LOGITS
     Slip
    0.27
    大大å°ıå°ı
    0.26
    èĤ¢
    0.25
    iah
    0.24
    ,[],
    0.23
    acen
    0.23
    åĬłå¿«å»ºè®¾
    0.23
    泡沫
    0.23
     knack
    0.23
    notation
    0.22
    Activations Density 47.365%

    No Known Activations