© 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. 41872
    Prev
    Next
    INDEX
    Explanations

    Assistant [followed by title or location]

    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
    人æĿ¥è¯´
    -0.09
    uréat
    -0.08
    ono
    -0.08
    asil
    -0.08
    /disable
    -0.08
    人äºĨ
    -0.08
    人ä¸Ń
    -0.08
    erp
    -0.08
    ات
    -0.08
    etc
    -0.08
    POSITIVE LOGITS
    ive
    0.07
    çĤ³
    0.07
    å§ĵ
    0.07
    aray
    0.07
    )__
    0.06
    isal
    0.06
    ows
    0.06
    à¥Ĥ
    0.06
    baugh
    0.06
    çļĦ
    0.06
    Activations Density 0.004%

    No Known Activations