© 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. 62036
    Prev
    Next
    INDEX
    Explanations

    units of measurement or currency

    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
    áz
    -0.07
    ane
    -0.06
    ä¸įå¤ĸ
    -0.06
    éĥ½åĢ¼å¾Ĺ
    -0.06
    éĻª
    -0.06
    awal
    -0.06
    å°Ĩæķ´ä¸ª
    -0.06
    öv
    -0.06
    ually
    -0.06
    gov
    -0.06
    POSITIVE LOGITS
    brig
    0.09
    ç¡®æľī
    0.08
    ->$
    0.07
    ulette
    0.07
    bab
    0.07
    室åĨħ设计
    0.07
    ]]=
    0.07
     wynosi
    0.07
    ahoma
    0.07
     averaged
    0.07
    Activations Density 0.015%

    No Known Activations