© 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. 40086
    Prev
    Next
    INDEX
    Explanations

    links receptors to a

    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
    ime
    -0.07
    -ng
    -0.07
    æĢĿéĩı
    -0.06
    æĥ³äºĨ解
    -0.06
    é¯
    -0.06
    OMA
    -0.06
    ×ķ׾×Ļ
    -0.06
    .tel
    -0.06
     /*!<
    -0.06
    æľ
    -0.06
    POSITIVE LOGITS
    代çłģå¦Ĥä¸ĭ
    0.08
    adra
    0.08
    warts
    0.08
    ä½ķæĸ¹
    0.07
    ç¨ĭåºıä¸Ń
    0.07
    æ¤Ĵ
    0.07
    æĩĤäºĨ
    0.07
    acic
    0.07
    åĭ¤
    0.07
    åģļæ³ķ
    0.07
    Activations Density 0.003%

    No Known Activations