© 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. 2959
    Prev
    Next
    INDEX
    Explanations

    stock, time, gang, accumulating

    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
    maak
    -0.08
    åıĮä¼ij
    -0.08
    æĹłåij³
    -0.07
     ÐłÐµÑĩÑĮ
    -0.07
    è§ĴéĢIJ
    -0.07
    unce
    -0.07
    uben
    -0.07
    лекÑģ
    -0.07
    gnore
    -0.07
    使èĩªå·±çļĦ
    -0.07
    POSITIVE LOGITS
    å¤ĸåľ¨
    0.07
     Stewart
    0.07
    ÑģÑĤÑĢом
    0.06
    иÑĤа
    0.06
    bv
    0.06
    åħ¬å¼ı
    0.06
    _hook
    0.06
    á
    0.06
    æī¾ä¸įåĪ°
    0.06
    天涯
    0.06
    Activations Density 0.002%

    No Known Activations