© 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. 32117
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or men/females

    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
     interp
    -0.08
    roz
    -0.07
    [Math
    -0.06
     sciences
    -0.06
    лÑİми
    -0.06
    ','=','
    -0.06
    ernels
    -0.06
    ä½łä¸įä¼ļ
    -0.06
    -comments
    -0.06
    Re
    -0.06
    POSITIVE LOGITS
    iland
    0.08
    andy
    0.08
    جاÙħ
    0.08
    飶
    0.08
    ayu
    0.08
    å°Ķå¾·
    0.07
    erti
    0.07
    kert
    0.07
    足çļĦ
    0.07
    anger
    0.07
    Activations Density 0.412%

    No Known Activations