© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20523
    Prev
    Next
    INDEX
    Explanations

    HTML tag attributes and structure

    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
    तà¥įया
    -0.07
    ated
    -0.07
    তা
    -0.07
    ockey
    -0.07
    æ§IJ
    -0.07
    kert
    -0.06
    AVING
    -0.06
    ziali
    -0.06
    bach
    -0.06
    efore
    -0.06
    POSITIVE LOGITS
    ï¼ļ</
    0.08
    åĬłæĭ¿å¤§
    0.08
    Ctr
    0.08
    èĩªå·±è¢«
    0.07
    èĩªå·±
    0.07
    èĩªå·±èº«ä¸Ĭ
    0.07
    lix
    0.07
    ÑıÑħ
    0.07
    essus
    0.07
    iano
    0.07
    Activations Density 0.119%

    No Known Activations