© 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. 98782
    Prev
    Next
    INDEX
    Explanations

    time

    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
    ä¸ĢéĹª
    -0.27
    ä¸Ģ线
    -0.26
    第ä¸ĢæŃ¥
    -0.24
    æĶ¿æ³ķ
    -0.24
    ambient
    -0.23
    igkeit
    -0.23
    erves
    -0.23
    á»ĥn
    -0.23
    :hover
    -0.23
     getCategory
    -0.23
    POSITIVE LOGITS
    æĸ°åŀĭ
    0.27
    ¼
    0.27
    æ°ijå¿ĥ
    0.26
     win
    0.26
    Window
    0.25
    _maximum
    0.24
    ä¹ĥ
    0.24
     Win
    0.24
     unde
    0.24
    大éĩı
    0.24
    Activations Density 0.009%

    No Known Activations