© 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. 49377
    Prev
    Next
    INDEX
    Explanations

    attacked, abducted from

    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
    ervis
    -0.08
    mara
    -0.07
    Unc
    -0.07
    chan
    -0.07
    ä¸ĭåIJĮ
    -0.07
    furt
    -0.07
    awe
    -0.07
    emp
    -0.07
    mith
    -0.06
     infin
    -0.06
    POSITIVE LOGITS
    è¡ĢèĤī
    0.08
    )!
    0.08
    ooks
    0.08
    幸äºı
    0.08
    åħ¨éĿ¢
    0.08
    æĢİä¹ĪåĬŀ
    0.07
    äºĨèµ·æĿ¥
    0.07
    ocks
    0.07
    çľģæŶ
    0.07
    _primitive
    0.07
    Activations Density 0.266%

    No Known Activations