© 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. 43505
    Prev
    Next
    INDEX
    Explanations

    cell references like A1, A2

    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
    ↵
    -0.07
    åĩºèĩª
    -0.06
    符åIJĪè¦ģæ±Ĥ
    -0.06
     "'
    -0.06
    åį±
    -0.06
    -0.06
    èĩª
    -0.05
     Pound
    -0.05
    æijĴå¼ĥ
    -0.05
     Stress
    -0.05
    POSITIVE LOGITS
    á»ĭt
    0.09
    èĬ³åįİ
    0.08
    éĩijé¦Ļ
    0.08
    undy
    0.08
    è¿ŀäºij
    0.08
    é¶
    0.08
    请注æĺİ
    0.08
    ä¸Ģ线çļĦ
    0.08
    éĿłè¿ij
    0.08
     grid
    0.08
    Activations Density 0.029%

    No Known Activations