© 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. 63967
    Prev
    Next
    INDEX
    Explanations

    Data, code, and predictions

    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
     onLoad
    -0.28
    åıĽ
    -0.26
    bian
    -0.26
    磼
    -0.25
    arness
    -0.25
    gie
    -0.25
    uler
    -0.24
     conserve
    -0.24
    \">
    -0.24
    åºĶæĶ¶è´¦æ¬¾
    -0.23
    POSITIVE LOGITS
    orage
    0.27
    ãł
    0.27
    容
    0.25
    人å¿ĥ
    0.24
    çļĦæĸĩåĮĸ
    0.24
    azole
    0.24
    ģ
    0.24
    /ag
    0.24
    ESCO
    0.24
    åŁºçĿ£å¾Ĵ
    0.24
    Activations Density 0.894%

    No Known Activations