© 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. 41843
    Prev
    Next
    INDEX
    Explanations

    separation

    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
    åĬłæĭ¿å¤§
    -0.10
    ä¸įè¡°
    -0.09
    /software
    -0.09
    sey
    -0.09
    rica
    -0.08
    reja
    -0.08
    ึ
    -0.08
    ymar
    -0.08
    antity
    -0.08
    eneral
    -0.08
    POSITIVE LOGITS
    /div
    0.09
    æĪij们ä¼ļ尽快
    0.08
    ately
    0.08
     khá»ıi
    0.08
    à¹ģ
    0.08
    able
    0.07
    ÑģÑĤоÑı
    0.07
    hips
    0.07
    ellite
    0.07
    íĨ±
    0.07
    Activations Density 0.038%

    No Known Activations