© 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. 13896
    Prev
    Next
    INDEX
    Explanations

    transaction state, language, filter, insiders, precautionary measures, programs

    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
    TRO
    -0.05
    î
    -0.05
    建ä¸ļ
    -0.05
    Picture
    -0.05
    ousy
    -0.05
    ẳng
    -0.05
    rome
    -0.05
    ...
    -0.05
    ä½łæķ¢
    -0.05
    trat
    -0.05
    POSITIVE LOGITS
    velt
    0.08
    icule
    0.07
    åīįè¿°
    0.07
    ë°Ľ
    0.06
    asten
    0.06
    ÙĬÙĦات
    0.06
    ovin
    0.06
    ANTE
    0.06
    ENTES
    0.06
    estero
    0.06
    Activations Density 1.686%

    No Known Activations