© 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. 61236
    Prev
    Next
    INDEX
    Explanations

    numbers or punctuation

    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
    urna
    -0.08
    eil
    -0.07
    ehl
    -0.06
    Exact
    -0.06
    loi
    -0.06
    åĽŀ乡
    -0.06
    éļĺ
    -0.06
    æŃ
    -0.06
    /english
    -0.06
    ä¸Ĭé£İ
    -0.06
    POSITIVE LOGITS
    adox
    0.08
    нове
    0.08
    éĥ½ä¸įæķ¢
    0.07
    fore
    0.07
    ule
    0.07
    scheme
    0.07
     Zone
    0.07
    endorf
    0.07
    ạch
    0.07
     Scenario
    0.07
    Activations Density 0.491%

    No Known Activations