© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8993
    Prev
    Next
    INDEX
    Explanations

    bibliographic citations

    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
    kot
    -0.07
    UBL
    -0.06
     Cv
    -0.06
    身为
    -0.06
    ubile
    -0.06
    loth
    -0.06
    ereg
    -0.06
    etto
    -0.06
    upa
    -0.06
    ìĭ
    -0.06
    POSITIVE LOGITS
    onal
    0.08
    ÑĢÑĥм
    0.08
    èĻ±
    0.08
    รà¹Īม
    0.08
    anson
    0.07
    à¹Ħà¸ģล
    0.07
    ights
    0.07
    æľªå¤®
    0.07
    çļĦå·¥ä½ľä½ľé£İ
    0.07
    éģ¥
    0.07
    Activations Density 0.017%

    No Known Activations