© 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. 57640
    Prev
    Next
    INDEX
    Explanations

    float-type, float-left, floating environments, floatables

    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
    imony
    -0.08
    ¦
    -0.08
    ëĬĺ
    -0.08
    ลฯ
    -0.07
    elman
    -0.07
    imonials
    -0.07
    ÑģÑĤоÑĢон
    -0.07
    ä¼Ĺå¿ĹæĪIJåŁİ
    -0.07
    zelf
    -0.07
    Äħż
    -0.07
    POSITIVE LOGITS
    اÙĭ
    0.09
    |int
    0.08
    enberg
    0.08
    èį¡èį¡
    0.08
    usercontent
    0.08
    ugal
    0.08
    croft
    0.08
    ÑģÑı
    0.07
    antly
    0.07
    ancy
    0.07
    Activations Density 0.035%

    No Known Activations