© 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. 23365
    Prev
    Next
    INDEX
    Explanations

    division, cases, samples

    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
     Howell
    -0.07
    reiber
    -0.07
    åįĪ
    -0.06
    æĹĭåį³
    -0.06
    MASK
    -0.06
    æĮ¡
    -0.06
    éĶī
    -0.06
    é£Łèį¯
    -0.06
    ä¸Ģä½ľ
    -0.06
    âĪĻ
    -0.06
    POSITIVE LOGITS
    å§Ķ
    0.08
    çļĦç¾İ好
    0.08
    åľ¨ä¸Ĭè¿°
    0.07
    imary
    0.07
    erver
    0.07
    åı¯æĢľçļĦ
    0.07
    ãĤ³ãĥŁ
    0.07
    iecz
    0.07
    çļĸ
    0.07
    ovic
    0.07
    Activations Density 0.003%

    No Known Activations