© 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. 26287
    Prev
    Next
    INDEX
    Explanations

    documentation and evidence

    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
    ä¸įæ²»
    -0.07
    óf
    -0.07
    Å¡lo
    -0.07
    ä¸İä¼Ĺ
    -0.07
    katan
    -0.07
    å§Ĩæĸ¯
    -0.06
    æŃ¤æ¬¾
    -0.06
    hips
    -0.06
    ctu
    -0.06
    cribes
    -0.06
    POSITIVE LOGITS
    è¯ģæĺİ
    0.12
    åİŁä»¶
    0.12
    å¤įåį°ä»¶
    0.12
    è¯ģæĺİæĸĩ件
    0.11
     подÑĤвеÑĢжда
    0.11
    è¯ģæĺİæĿIJæĸĻ
    0.10
     evidence
    0.10
     documents
    0.10
    é½IJåħ¨
    0.10
     proof
    0.10
    Activations Density 0.053%

    No Known Activations