© 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. 20-TRANSCODER-HP
    7. 142044
    Prev
    Next
    INDEX
    Explanations

    systems/technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ½ä¸įä¼ļ
    -0.26
    anything
    -0.26
    imentary
    -0.25
    æĿĤ
    -0.25
     anything
    -0.24
    éĿĴ
    -0.24
    çIJĨäºĭéķ¿
    -0.24
    ãģĤãģŁãĤĬ
    -0.24
    %B
    -0.24
     exp
    -0.23
    POSITIVE LOGITS
    è¼Ŀ
    0.30
    ayı
    0.29
    vu
    0.28
    SX
    0.28
    è¾ī
    0.28
    ÐĵлавнаÑı
    0.27
    знаÑĩ
    0.26
    ayload
    0.25
    è¿Ļæł·çļĦè¯Ŀ
    0.25
    éĶ£
    0.25
    Activations Density 63.999%

    No Known Activations