© 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. 17895
    Prev
    Next
    INDEX
    Explanations

    trends, rates, evolution, pace

    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
    个èµŀ
    -0.08
     diserta
    -0.08
    è¯ģåĪ¸èĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.07
    ÐĿÐł
    -0.07
    (er
    -0.07
    çĪ·
    -0.07
    æ¼Ķåĩº
    -0.07
     theirs
    -0.07
    .nr
    -0.07
    rong
    -0.07
    POSITIVE LOGITS
     extrapol
    0.17
    è§Ħå¾ĭ
    0.14
     trend
    0.11
    è§Ħå¾ĭçļĦ
    0.11
    è¶ĭåĬ¿
    0.11
     pattern
    0.11
     consistent
    0.10
    æݨç®Ĺ
    0.10
    çļĦè¶ĭåĬ¿
    0.10
     linear
    0.10
    Activations Density 0.055%

    No Known Activations