© 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. 24809
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    缸åħ³åĨħ容
    -0.08
    çļĦ缸åħ³ä¿¡æģ¯
    -0.08
    ooth
    -0.08
    缸åħ³éĹ®é¢ĺ
    -0.08
    æĶ¾çŁ¢
    -0.07
    缸åħ³æ³ķå¾ĭ责任
    -0.07
     noticeably
    -0.07
    ähn
    -0.07
    çļĦ缸åħ³çŁ¥è¯Ĩ
    -0.07
     presta
    -0.07
    POSITIVE LOGITS
    çIJĨåºĶ
    0.08
    é¢ĺæĦı
    0.08
     logique
    0.08
    éĢ»è¾ij
    0.07
     logic
    0.07
     lógica
    0.07
    輩
    0.07
    راÙħ
    0.07
    éº
    0.07
     müsste
    0.07
    Activations Density 0.024%

    No Known Activations