© 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. 27099
    Prev
    Next
    INDEX
    Explanations

    prompt questions or calls

    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
    æĹłè¸ª
    -0.07
    åıĬæĹ¶è§£åĨ³
    -0.07
    æľīéģĵ
    -0.07
    ault
    -0.07
    гÑĢад
    -0.07
    踪影
    -0.07
    olt
    -0.07
    clin
    -0.07
     rebound
    -0.07
    ECT
    -0.07
    POSITIVE LOGITS
    è¦ģæ±Ĥè¿Ľè¡Į
    0.08
    ocache
    0.07
    isle
    0.07
    abra
    0.07
    sters
    0.07
    ulated
    0.07
    zis
    0.07
    åĦ¿
    0.07
    pur
    0.06
    çļĦéĩįçĤ¹
    0.06
    Activations Density 0.003%

    No Known Activations