© 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. 25-TRANSCODER-HP
    7. 108873
    Prev
    Next
    INDEX
    Explanations

    scientific measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avior
    -0.30
    ython
    -0.26
    al
    -0.25
    éĵ¶
    -0.24
    celand
    -0.24
    smith
    -0.24
    ismet
    -0.24
    oen
    -0.23
    ä¸ĢåĽŀäºĭ
    -0.23
    人
    -0.23
    POSITIVE LOGITS
    èĥ½åĬĽåĴĮ
    0.28
    åĴĮå®ĮåĸĦ
    0.27
     transparency
    0.27
    æĪIJé¾Ļ
    0.26
     Weiner
    0.25
     risking
    0.25
     {},↵
    0.24
    /show
    0.24
     risk
    0.24
    åĪĽæĸ°èĥ½åĬĽ
    0.24
    Activations Density 0.187%

    No Known Activations