© 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. 60318
    Prev
    Next
    INDEX
    Explanations

    invention

    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
    åħ³æ³¨æĪij们
    -0.08
    νÏĮ
    -0.08
    ascar
    -0.07
    elaar
    -0.07
    æĬĬ人
    -0.07
    ë²Į
    -0.07
     sejenis
    -0.07
    è±ļ
    -0.07
    ihi
    -0.07
     Bundy
    -0.07
    POSITIVE LOGITS
    ัà¹Īà¸Ļ
    0.07
    sour
    0.07
     foul
    0.06
     Saga
    0.06
    ä¸ĩéĩĮ
    0.06
    rc
    0.06
     moreover
    0.06
    çĢ
    0.06
    çĩ
    0.06
    acre
    0.06
    Activations Density 0.099%

    No Known Activations