© 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. 27-TRANSCODER-HP
    7. 7810
    Prev
    Next
    INDEX
    Explanations

    has/had

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çŁ¥éģĵäºĨ
    -0.30
     window
    -0.30
     Window
    -0.27
    åħ¬åħ±åľºæīĢ
    -0.27
    çªĹåı£
    -0.26
    aten
    -0.25
    idian
    -0.25
    æŶä¸į
    -0.24
     using
    -0.24
    äºĨè§£æĽ´å¤ļ
    -0.24
    POSITIVE LOGITS
     goal
    0.29
    licos
    0.27
    èī¯
    0.26
     erfolgreich
    0.26
    æĥĬ
    0.25
    goal
    0.25
    é¢ł
    0.25
    HandlerContext
    0.25
    rones
    0.24
    -good
    0.24
    Activations Density 0.007%

    No Known Activations