© 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. 51477
    Prev
    Next
    INDEX
    Explanations

    JSON structure delimiters

    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
    ¢
    -0.08
    æľīæĸ°çļĦ
    -0.06
    ä½ĵåĨħçļĦ
    -0.06
    ä¼ĺ
    -0.06
    tuk
    -0.06
    ivière
    -0.06
    好çĶ¨
    -0.06
     Definition
    -0.06
    æľīç»Ħç»ĩ
    -0.06
     assort
    -0.06
    POSITIVE LOGITS
    Ïĥκ
    0.08
    equal
    0.08
    adir
    0.08
    ELD
    0.08
     nhãn
    0.08
    htag
    0.08
    ek
    0.07
    eba
    0.07
    aths
    0.07
    åĨ²å¤©
    0.07
    Activations Density 0.002%

    No Known Activations