© 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. 130432
    Prev
    Next
    INDEX
    Explanations

    patient

    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
    lando
    -0.27
    ÇĶ
    -0.26
     Van
    -0.26
    ä»»åĬ¡
    -0.26
    çIJĨ解
    -0.26
    äºĭçī©
    -0.26
    çIJĨ解åĴĮ
    -0.26
     Kent
    -0.25
    æĸĩåŃĹ
    -0.24
    大åѦ
    -0.24
    POSITIVE LOGITS
    è¯Ħä»·
    0.27
    .eval
    0.27
    .gdx
    0.26
    è¹Ĭ
    0.26
    	eval
    0.26
    Evaluation
    0.25
     Evaluation
    0.25
     evaluation
    0.25
    Evaluator
    0.25
    å¥İ
    0.25
    Activations Density 26.969%

    No Known Activations