© 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. 11833
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers and sqrt

    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
    Õ²
    -0.07
    ocode
    -0.06
    hofer
    -0.06
    ÑĤоÑĢ
    -0.06
    æ¸¸ä¾ł
    -0.06
    éĢĨ
    -0.06
    äºİå¿ĥ
    -0.06
    Camp
    -0.06
    omp
    -0.06
    cim
    -0.06
    POSITIVE LOGITS
    æĶ¶èĹıæľ¬ç«Ļ
    0.09
    åIJĵ人
    0.08
    ÑģÑĤила
    0.08
     peril
    0.08
    oney
    0.08
    emui
    0.08
    ward
    0.07
    onest
    0.07
    .Observable
    0.07
     tÃłu
    0.07
    Activations Density 0.013%

    No Known Activations