© 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. 61242
    Prev
    Next
    INDEX
    Explanations

    eye correction and vision

    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
     обÑģÑĤоÑı
    -0.08
    æ·«
    -0.08
    _tail
    -0.07
    æ³°è¾¾
    -0.07
    OrElse
    -0.07
    .tail
    -0.07
    åİĭåĬĽå¤§
    -0.07
    -process
    -0.07
    onner
    -0.07
    åıĸè¯ģ
    -0.07
    POSITIVE LOGITS
    éķľçīĩ
    0.09
    æį¢ç®Ĺ
    0.07
    对è§Ĩ
    0.07
    磫æŃ£
    0.07
    è´Ł
    0.07
    è´ŁçļĦ
    0.07
     negative
    0.07
     verg
    0.07
     roman
    0.07
     twe
    0.07
    Activations Density 0.006%

    No Known Activations