© 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. 34588
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    äºĨ大éĩı
    -0.08
    大éĩıçļĦ
    -0.08
    çļĦ大éĩı
    -0.08
    大éĩı
    -0.08
    äºĨ大éĩıçļĦ
    -0.07
    çª
    -0.07
    >[]
    -0.07
    beck
    -0.07
    æľī大éĩı
    -0.06
    æľīå¾Īå¤ļ人
    -0.06
    POSITIVE LOGITS
    akaan
    0.08
    Ù¾ÛĮ
    0.08
     pulsa
    0.07
    óp
    0.07
    itore
    0.07
    elsen
    0.07
    abis
    0.07
     mere
    0.07
    éĤĢ
    0.07
    peen
    0.06
    Activations Density 0.012%

    No Known Activations