© 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. 32345
    Prev
    Next
    INDEX
    Explanations

    technical terms for processes or components

    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
    íĻĶëIJľ
    -0.08
    ë¡Ģ
    -0.07
    attes
    -0.07
    ichtigen
    -0.07
    æľ¨åħ°
    -0.06
    onel
    -0.06
    ìłģìĿ´ê³ł
    -0.06
    elier
    -0.06
    Duplicates
    -0.06
    казÑĭваеÑĤÑģÑı
    -0.06
    POSITIVE LOGITS
    rot
    0.07
    hood
    0.07
    haus
    0.07
    æģ¤
    0.07
    ä¸į误
    0.07
    æĦ§
    0.07
    ani
    0.07
    undi
    0.07
    rone
    0.07
    Äģv
    0.06
    Activations Density 0.734%

    No Known Activations