© 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. 45292
    Prev
    Next
    INDEX
    Explanations

    during or after events

    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
    并ä¸į容æĺĵ
    -0.07
    illi
    -0.07
    æ§ĺãģ®
    -0.07
    以æıIJé«ĺ
    -0.07
    nak
    -0.07
    çĶ·æĢ§çļĦ
    -0.07
    å¸ĮæľĽå¯¹å¤§å®¶
    -0.07
    ellino
    -0.07
    allo
    -0.07
    转载请注æĺİ
    -0.07
    POSITIVE LOGITS
     various
    0.07
     versus
    0.07
    缸åħ³æĥħåĨµ
    0.07
    åıĺåĮĸæĥħåĨµ
    0.07
    ç»Ļå®ļ
    0.07
    umerator
    0.07
    ÙĪÙħا
    0.07
    given
    0.07
     given
    0.06
     vs
    0.06
    Activations Density 0.258%

    No Known Activations