© 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. 61982
    Prev
    Next
    INDEX
    Explanations

    change or expansion

    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
    çļĦåıĺåĮĸ
    -0.09
    åıĺåĮĸåĴĮ
    -0.08
    ä¹ĭå·®
    -0.08
    çļĦ好æľĭåıĭ
    -0.07
    ellis
    -0.07
    æĸ°æĸ¹æ³ķ
    -0.07
    ipas
    -0.07
    åıĺåĮĸ
    -0.07
    edis
    -0.07
    åľ¨åŃ¦ä¹łä¸Ń
    -0.07
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.09
     ÙĤÙĦÙĬ
    0.09
    åħ¶
    0.09
     ÙħؤÙĤت
    0.08
    åİŁæľī
    0.08
     overall
    0.08
    /add
    0.08
     their
    0.08
    /Add
    0.08
    åĴĮä¼ĺåĮĸ
    0.08
    Activations Density 0.284%

    No Known Activations