© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    of this

    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
    á»Ńa
    -0.08
    <tool_response>
    -0.08
    åĩºä¸ĢæĿ¡
    -0.07
    stime
    -0.07
    缮çŀª
    -0.07
    æŶæĹ¥
    -0.07
    ä¸įåħ¥
    -0.07
    æ£Ĵ
    -0.07
    duino
    -0.07
    çĽ£çĿ£
    -0.07
    POSITIVE LOGITS
    yy
    0.08
    ook
    0.07
    iams
    0.07
    åĽ½åħ¬
    0.07
    ici
    0.07
    ç«£
    0.06
    -language
    0.06
    жнÑı
    0.06
    æłĩçļĦçī©
    0.06
    å£Į
    0.06
    Activations Density 1.058%

    No Known Activations