© 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. 108171
    Prev
    Next
    INDEX
    Explanations

    say "0"

    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
    æĺ¯ä»İ
    -0.30
    ;
    -0.29
    ìĿĦ
    -0.28
    ,
    -0.27
     to
    -0.27
     for
    -0.27
     when
    -0.27
    ãĤĴ
    -0.26
    æŶ
    -0.26
     ÙħÙĨÙĩا
    -0.26
    POSITIVE LOGITS
    ippers
    0.31
    illions
    0.27
     acknowled
    0.27
    çľģéĴ±
    0.27
    indered
    0.27
    Ļ¨
    0.26
     nutshell
    0.25
     custody
    0.25
    лÑıÑĢ
    0.25
    ispers
    0.25
    Activations Density 1.418%

    No Known Activations