© 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. 48902
    Prev
    Next
    INDEX
    Explanations

    lists, set, collection, and relationship 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
    æĬķåħ¥
    -0.08
    ettle
    -0.07
    observer
    -0.07
    vale
    -0.07
    éĩįéĺ³
    -0.07
     manc
    -0.07
    æĻĸ
    -0.06
     Observatory
    -0.06
     Asia
    -0.06
    .createFrom
    -0.06
    POSITIVE LOGITS
     lists
    0.09
    æ´
    0.08
    lists
    0.08
     list
    0.08
    ç±
    0.08
    utch
    0.07
    æİ¥åĪ°
    0.07
    Chief
    0.07
    ä¼Ĺ
    0.07
    åĨħ容丰å¯Į
    0.07
    Activations Density 0.042%

    No Known Activations