© 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. 61678
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    è¿Ŀåıįä¸Ĭè¿°
    -0.09
    æĺł
    -0.08
    antor
    -0.07
    رÙĥ
    -0.07
    его
    -0.07
    ServerError
    -0.07
    cesi
    -0.07
    ç£
    -0.07
     downstairs
    -0.07
     verst
    -0.07
    POSITIVE LOGITS
    where
    0.09
     where
    0.08
    åħ¶ä¸Ń
    0.08
    å®ļå¾ĭ
    0.07
     applicable
    0.07
     wherein
    0.07
    èĤ²æīį
    0.07
    licable
    0.07
    å¼ıä¸Ń
    0.07
     Where
    0.06
    Activations Density 0.018%

    No Known Activations