© 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. 11105
    Prev
    Next
    INDEX
    Explanations

    versions, copies, editions, translations

    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
    ä½ľè¯į
    -0.08
    Rated
    -0.07
    èµĬ
    -0.07
     diplôm
    -0.07
    ç»ĵä¸ļ
    -0.07
    å¹´åįĬ
    -0.07
     descrit
    -0.07
    è¾
    -0.07
    éĨĴäºĨ
    -0.07
     Pett
    -0.07
    POSITIVE LOGITS
     versions
    0.14
    çīĪæľ¬
    0.13
     version
    0.13
    çļĦçīĪæľ¬
    0.12
     copies
    0.11
    version
    0.10
     editions
    0.10
     Versions
    0.10
     edition
    0.10
    /version
    0.10
    Activations Density 0.157%

    No Known Activations