© 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. 107739
    Prev
    Next
    INDEX
    Explanations

    USA and its structure

    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
    oga
    -0.26
    å¾Ĺå¤ļ
    -0.26
    éł»
    -0.25
    çļĦé£İéĻ©
    -0.25
    _via
    -0.25
     ($)
    -0.25
    ogh
    -0.24
     prayed
    -0.24
    ogr
    -0.23
    paginator
    -0.23
    POSITIVE LOGITS
    æĹ¢èĥ½
    0.28
    ç§ķ
    0.27
    Drop
    0.27
     diamond
    0.26
    à¹ģ
    0.26
    ç°ª
    0.25
    Simple
    0.25
     disen
    0.25
    олÑĮ
    0.24
     offering
    0.24
    Activations Density 10.743%

    No Known Activations