© 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. 30115
    Prev
    Next
    INDEX
    Explanations

    gradually increasing or diminishing

    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
    æľīæĦıä¹ī
    -0.08
     ном
    -0.08
    åѦéĻ¢éĻ¢éķ¿
    -0.08
    ahlt
    -0.08
    rieg
    -0.07
    izzi
    -0.07
    pun
    -0.07
    .signals
    -0.07
    erry
    -0.07
    itti
    -0.07
    POSITIVE LOGITS
    éĢĴå¢ŀ
    0.11
    éĢIJ漸
    0.09
    æĦĪæĿ¥æĦĪ
    0.08
    è¶ĬæĿ¥è¶Ĭå¤ļçļĦ
    0.08
     progressively
    0.08
    éĢIJæ¸IJ
    0.08
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    0.08
     crescendo
    0.08
     gradually
    0.08
     cresc
    0.08
    Activations Density 0.019%

    No Known Activations