© 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. 129509
    Prev
    Next
    INDEX
    Explanations

    ..

    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
    æį¢
    -0.31
     Vest
    -0.27
     Trail
    -0.26
    åıij
    -0.26
     triang
    -0.25
     un
    -0.24
    è¿Ļæł·è¯´
    -0.24
    å½ĴæĿ¥
    -0.24
    è¦ģæľī
    -0.23
     legal
    -0.23
    POSITIVE LOGITS
    Surname
    0.27
    ographics
    0.25
    hält
    0.25
    -widgets
    0.23
     Incorporated
    0.23
    ä¸Ģç¢Ĺ
    0.23
    inet
    0.23
    ène
    0.23
    èĥª
    0.23
    åķľ
    0.23
    Activations Density 0.001%

    No Known Activations