© 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. 22972
    Prev
    Next
    INDEX
    Explanations

    months

    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
    æ¯ıå¹´
    -0.32
    å¹´èµ·
    -0.30
    åİĨå¹´
    -0.30
    éĢIJå¹´
    -0.27
     saja
    -0.26
    注åħ¥
    -0.26
     incidence
    -0.26
     sang
    -0.26
     past
    -0.26
    æ¯ıå¹´éĥ½
    -0.25
    POSITIVE LOGITS
    rails
    0.28
    appable
    0.27
     errs
    0.27
    bish
    0.27
    Meet
    0.26
     manh
    0.26
    èĤº
    0.25
    è§ģéĿ¢
    0.25
    READING
    0.24
    Meeting
    0.24
    Activations Density 0.006%

    No Known Activations