© 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. 42665
    Prev
    Next
    INDEX
    Explanations

    metal salts and chemical compounds

    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
    agg
    -0.08
    éĶĢ
    -0.07
    åħ³éĹŃçªĹåı£
    -0.07
    åĨ
    -0.07
    æ°ĵ
    -0.06
    ann
    -0.06
    éŁ³
    -0.06
    åĪ°èĢģ
    -0.06
    é³ŀ
    -0.06
    .squeeze
    -0.06
    POSITIVE LOGITS
     Crosby
    0.08
    _COMPLEX
    0.08
    溶液ä¸Ń
    0.07
    etje
    0.07
    åĩºåĵģçļĦ
    0.07
    ezas
    0.07
    常åIJĥ
    0.07
    hare
    0.07
    _href
    0.07
    åĻ¨æĿIJ
    0.07
    Activations Density 0.019%

    No Known Activations