© 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. 26407
    Prev
    Next
    INDEX
    Explanations

    comprehensive analysis

    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
    ting
    -0.09
    zinho
    -0.08
    sWith
    -0.08
    ë§ĪìŀIJ
    -0.08
    -même
    -0.08
    omi
    -0.07
    uation
    -0.07
    opard
    -0.07
    deos
    -0.07
    paro
    -0.07
    POSITIVE LOGITS
    åħ¶äºĭ
    0.08
     enough
    0.08
    es
    0.08
    åħ¨éĿ¢çļĦ
    0.08
    ed
    0.07
    ible
    0.07
    ensible
    0.07
    ider
    0.07
    ãģªãģĮ
    0.07
    -minded
    0.07
    Activations Density 0.024%

    No Known Activations