© 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. 32414
    Prev
    Next
    INDEX
    Explanations

    adult cat, strict declaration

    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
    ombat
    -0.10
    FRING
    -0.09
    ä½łåı¯èĥ½
    -0.08
    abbo
    -0.08
    è¡Ģèħ¥
    -0.08
    chas
    -0.08
    绣ä¸Ģå®īæİĴ
    -0.08
    bene
    -0.08
    tores
    -0.08
    stum
    -0.08
    POSITIVE LOGITS
    ä¼¼çļĦ
    0.07
     or
    0.07
    NASDAQ
    0.06
    å¼ıçļĦ
    0.06
    -like
    0.06
    äºĪ
    0.06
    å°Ķå¾·
    0.06
    acht
    0.06
    -style
    0.06
    naire
    0.06
    Activations Density 0.001%

    No Known Activations