© 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. 130077
    Prev
    Next
    INDEX
    Explanations

    by, through, or via

    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
    agara
    -0.27
    ugo
    -0.25
     SOFTWARE
    -0.25
    ç¼£
    -0.24
    åĽ¾çĶ»
    -0.24
     fundamentally
    -0.24
    oug
    -0.24
    ilden
    -0.24
    addock
    -0.24
    landers
    -0.24
    POSITIVE LOGITS
    主æĮģ人
    0.28
     hors
    0.27
    åij½ä¸Ń
    0.26
    æĴ¬
    0.24
    èĥ½åĬĽå¼º
    0.24
    (always
    0.24
     L
    0.23
     Original
    0.23
     ré
    0.23
     uns
    0.23
    Activations Density 20.918%

    No Known Activations