© 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. 42263
    Prev
    Next
    INDEX
    Explanations

    first, last, second, third, sequence

    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
    /Page
    -0.08
    å½ĵæŶçļĦ
    -0.07
    èĥĮåIJİçļĦ
    -0.07
    模å¼ıåĴĮ
    -0.07
    chriften
    -0.07
    _BOTH
    -0.07
    åĸ±
    -0.07
    ãģ´
    -0.07
    æѤåīįçļĦ
    -0.07
    uar
    -0.07
    POSITIVE LOGITS
    most
    0.08
    çݯèĬĤ
    0.07
    odiac
    0.07
    ë²Ī
    0.07
    -last
    0.07
     esetben
    0.07
    åĴĮæľĢ
    0.07
    -ci
    0.07
    /original
    0.07
    éļĭ
    0.07
    Activations Density 0.026%

    No Known Activations