© 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. 3701
    Prev
    Next
    INDEX
    Explanations

    validation and testing

    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
    ekar
    -0.08
    è¯Ŀ说
    -0.07
    abouts
    -0.07
    çĪ±å°Ķ
    -0.07
    .native
    -0.07
    наÑģÑĤоÑı
    -0.07
    agia
    -0.07
    bauer
    -0.07
    ä¸Ģæ°Ķ
    -0.07
    æľ¬é¢ĺåĪĨæŀIJ
    -0.07
    POSITIVE LOGITS
    举æĿ¯
    0.07
    uth
    0.07
     ìĺĪ를
    0.07
    对ä¸ĢäºĽ
    0.06
    onder
    0.06
    å¾®è§Ĥ
    0.06
    æĻĸ
    0.06
    ä¸İå®ŀéĻħ
    0.06
    ict
    0.06
    对äºİä¸ĢäºĽ
    0.06
    Activations Density 0.003%

    No Known Activations