Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 15281
    Prev
    Next
    INDEX
    Explanations

    Data or structured information snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endors
    -0.26
    bsub
    -0.25
     mandated
    -0.25
     mandates
    -0.25
     Mand
    -0.25
    miss
    -0.25
    odule
    -0.24
    hoc
    -0.24
     sister
    -0.24
    _subs
    -0.24
    POSITIVE LOGITS
    око
    0.27
    loom
    0.27
    ledo
    0.26
    лиÑĤ
    0.26
    cke
    0.26
    ÊŁ
    0.25
     dap
    0.23
    ฤ
    0.23
    grading
    0.23
    纮
    0.23
    Activations Density 0.962%

    No Known Activations