© 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. 22-TRANSCODER-HP
    7. 112477
    Prev
    Next
    INDEX
    Explanations

    Sleep and insomnia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ization
    -0.27
    ä¸ŀ
    -0.25
    ouch
    -0.25
    åºĹéĵº
    -0.25
    åŁİåİ¿
    -0.25
    xfe
    -0.24
    ODO
    -0.24
    èıľ
    -0.24
    æĢ»æķ°
    -0.24
    æĭľ
    -0.24
    POSITIVE LOGITS
    æĸ¯å¡Ķ
    0.30
    Recovered
    0.25
    ળ
    0.24
     trì
    0.24
    Contrib
    0.23
    çļĦ好
    0.23
    éĢħ
    0.23
    Rare
    0.23
    _bal
    0.23
     rare
    0.23
    Activations Density 0.009%

    No Known Activations