© 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. 24738
    Prev
    Next
    INDEX
    Explanations

    examples, synonyms, or definitions

    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
    åĴĢ
    -0.09
    çĶ·å¥³ä¸įéĻIJ
    -0.07
    uates
    -0.07
    åķĨä¼ļ
    -0.07
    èĪ
    -0.07
    tribu
    -0.07
    è¿«
    -0.07
    mack
    -0.07
    /releases
    -0.07
    çļĦ人äºĨ
    -0.07
    POSITIVE LOGITS
    ulton
    0.07
    好æĥ³
    0.07
    forge
    0.07
    vron
    0.07
    SHA
    0.06
    ough
    0.06
    conomy
    0.06
    verz
    0.06
    çĥĤ漫
    0.06
    CFG
    0.06
    Activations Density 0.006%

    No Known Activations