© 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. 17827
    Prev
    Next
    INDEX
    Explanations

    Supreme Court

    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
    åľŁèĢ³
    -0.08
    phia
    -0.08
     newsp
    -0.08
    çľģå§Ķ书记
    -0.08
    ussy
    -0.08
    newValue
    -0.08
    謡
    -0.07
    æľ¬ç½ij
    -0.07
    eware
    -0.07
    æ¢Ŀ款
    -0.07
    POSITIVE LOGITS
    åĬŀåħ¬åİħ
    0.08
    ç»Ī审
    0.06
    åĨ³å®ļ
    0.06
     cap
    0.06
     Pend
    0.06
     members
    0.06
     ret
    0.06
     Priv
    0.06
     atom
    0.06
    ä»ĭåħ¥
    0.06
    Activations Density 0.551%

    No Known Activations