© 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. 34061
    Prev
    Next
    INDEX
    Explanations

    import

    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
    hood
    -0.11
    pherd
    -0.10
    ligt
    -0.09
    ipped
    -0.08
    erness
    -0.08
    poÅĽred
    -0.08
    estens
    -0.08
    istics
    -0.08
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.08
    ÑĨкого
    -0.08
    POSITIVE LOGITS
    antly
    0.10
    /export
    0.09
    anto
    0.08
    ãĤ¥
    0.08
    ãģħ
    0.08
    ed
    0.08
    unately
    0.08
    صاص
    0.07
    unate
    0.07
    alat
    0.07
    Activations Density 0.100%

    No Known Activations