© 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. 28641
    Prev
    Next
    INDEX
    Explanations

    and negative, out, females, exit

    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
    ä¸İåħ¶å®ĥ
    -0.07
    ä¸İæĸ°
    -0.07
    èĪĩåħ¶ä»ĸ
    -0.07
    elters
    -0.06
    ÑĢÑĥг
    -0.06
    ä¸İä¼łç»Ł
    -0.06
    ä¸İåħ¶ä»ĸ
    -0.06
    建议书
    -0.06
    ä¸İå°ı
    -0.06
    ä¸İçݰ代
    -0.06
    POSITIVE LOGITS
    /or
    0.10
    thon
    0.09
    acles
    0.09
    /of
    0.08
    ideo
    0.08
    峪
    0.08
    ê³
    0.08
    å·©
    0.08
    çıij
    0.07
    {id
    0.07
    Activations Density 0.207%

    No Known Activations