© 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. 41029
    Prev
    Next
    INDEX
    Explanations

    the noun

    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
    åį«ä¸ľ
    -0.08
    .sigmoid
    -0.08
    微信æī«ä¸Ģæī«
    -0.08
    âĨ³
    -0.08
    entang
    -0.08
     wireType
    -0.08
    inish
    -0.08
    ÑħваÑĤ
    -0.07
    ÏĥÏĦά
    -0.07
    æĥ®
    -0.07
    POSITIVE LOGITS
     Guz
    0.07
    arto
    0.07
    (
    0.06
    å®ŀä¾ĭ
    0.06
    uggy
    0.06
    uah
    0.06
    æĭ¬åı·
    0.06
    å°Ķé¡¿
    0.06
     Bret
    0.06
    ÙĥÙħا
    0.06
    Activations Density 0.003%

    No Known Activations