© 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. 12-TRANSCODER-HP
    7. 23219
    Prev
    Next
    INDEX
    Explanations

    Attention, alertness, vigilance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rão
    -0.27
    åĪ«
    -0.26
    å¾Ĺ天
    -0.25
    antor
    -0.25
    iros
    -0.25
    æµģéĢļ
    -0.24
    RARY
    -0.24
    kontakte
    -0.24
    è´
    -0.23
    ç©ij
    -0.23
    POSITIVE LOGITS
     vigil
    0.32
    guard
    0.27
    ç¼°
    0.27
     вним
    0.26
     attent
    0.26
     vigilant
    0.26
     Witnesses
    0.25
    hek
    0.25
    èĢ³æľµ
    0.25
    åħ¨éĿ¢æİ¨è¿Ľ
    0.24
    Activations Density 0.002%

    No Known Activations