© 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. 64711
    Prev
    Next
    INDEX
    Explanations

    Technology and health

    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
    纵横
    -0.26
    ç¸
    -0.25
    rut
    -0.25
    cie
    -0.25
    itas
    -0.25
    quito
    -0.25
    urious
    -0.25
    orate
    -0.24
    éĽħ
    -0.23
    _cr
    -0.23
    POSITIVE LOGITS
    æľ¬èº«
    0.28
    æľ¬èº«çļĦ
    0.27
    èĻ½çĦ¶
    0.27
    å·²ç»ıè¾¾åĪ°
    0.27
    第äºĮç§į
    0.26
     Thumbnails
    0.26
     default
    0.25
    noon
    0.24
    ıdır
    0.24
    eger
    0.24
    Activations Density 28.016%

    No Known Activations