© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22055
    Prev
    Next
    INDEX
    Explanations

    enter into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avanc
    -0.08
     wszystkim
    -0.07
    lettes
    -0.07
    KHR
    -0.07
    lette
    -0.07
    çªŁ
    -0.07
    课ä¸Ĭ
    -0.07
    áĢ¶
    -0.07
    faction
    -0.07
    ãĤ¸ãĤ¢
    -0.07
    POSITIVE LOGITS
    prises
    0.12
    prising
    0.12
    çľ¼å¸ĺ
    0.11
    /out
    0.11
     fray
    0.10
    psilon
    0.10
    æŃ£è½¨
    0.10
    into
    0.10
     into
    0.10
     INTO
    0.10
    Activations Density 0.048%

    No Known Activations