© 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. 18834
    Prev
    Next
    INDEX
    Explanations

    angular momentum or charge

    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
    åĽłåľ°
    -0.08
     vari
    -0.08
    svar
    -0.08
    OLS
    -0.08
    êµ´
    -0.08
    å¸Ĥåľºç«ŀäºī
    -0.08
    วิล
    -0.07
    åĦª
    -0.07
    rafo
    -0.07
    ingas
    -0.07
    POSITIVE LOGITS
     ë¶ĢìŬ
    0.08
    å®ĪæģĴ
    0.08
    ä»ĩ
    0.07
    á»Ļ
    0.07
     parity
    0.07
     conservation
    0.07
     assigned
    0.07
    parity
    0.06
    åĵ¡
    0.06
     lifetime
    0.06
    Activations Density 0.003%

    No Known Activations