© 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. 30766
    Prev
    Next
    INDEX
    Explanations

    league championships

    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
    ì¹Ļ
    -0.08
    vil
    -0.08
    Third
    -0.07
     synthesis
    -0.07
    ä¿Ĭ
    -0.07
    模æĭŁè¯ķé¢ĺ
    -0.07
     nas
    -0.07
    å¯¹çĽ¸åħ³
    -0.06
    -times
    -0.06
    inicio
    -0.06
    POSITIVE LOGITS
    اط
    0.08
    éĶĻ
    0.08
    æĪ·æĻĵ
    0.07
    åĪ°è¿Ļ
    0.07
    é£İéĻ©æݧåĪ¶
    0.07
    åĩºèº«çļĦ
    0.07
    ahas
    0.07
    ارش
    0.07
    èī¯
    0.07
    æī¾åĪ°èĩªå·±
    0.07
    Activations Density 0.016%

    No Known Activations