© 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. 2639
    Prev
    Next
    INDEX
    Explanations

    Tanner stages, serological, radiographic, girls, dementia

    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
    åĴĮç»´æĬ¤
    -0.07
    èİĺ
    -0.07
    NUM
    -0.07
    _keep
    -0.07
     Decl
    -0.07
    asha
    -0.07
    被åħ³éĹŃ
    -0.07
    åIJīæĸ¯
    -0.07
    _again
    -0.07
    otal
    -0.07
    POSITIVE LOGITS
    å·²ç»ıå¼Ģå§ĭ
    0.15
    åĪļåĪļå¼Ģå§ĭ
    0.13
    åĪļå¼Ģå§ĭ
    0.13
    å·²å¼Ģå§ĭ
    0.13
    Late
    0.13
     gradually
    0.13
    æīįå¼Ģå§ĭ
    0.13
    å¼Ģå§ĭåĩºçİ°
    0.13
    éĢIJæ¸IJ
    0.12
    æĪIJçĨŁ
    0.12
    Activations Density 0.283%

    No Known Activations