© 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. 3831
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    éĻ¤å¤ĸ
    -0.07
     latter
    -0.07
    haupt
    -0.06
    ariant
    -0.06
     correct
    -0.06
    aa
    -0.06
    width
    -0.06
    æĹ¥çĽ®
    -0.06
    ets
    -0.06
    åŃIJåĴĮ
    -0.06
    POSITIVE LOGITS
     pula
    0.08
    inste
    0.08
    arco
    0.07
    ãĥ«ãĤ¯
    0.07
    ä¸Ī
    0.07
    æĬĢæľ¯çĽijçĿ£
    0.07
    æľ¬å±±
    0.07
    yss
    0.07
     coord
    0.07
    缴æİ¥æĪĸ
    0.07
    Activations Density 0.020%

    No Known Activations