© 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. 16783
    Prev
    Next
    INDEX
    Explanations

    symbol, specific, 's

    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
     Hug
    -0.07
    ä¸Ńæĸĩç½ij
    -0.07
    zé
    -0.07
    åij½åIJįçļĦ
    -0.07
    çĶ©
    -0.07
     dereg
    -0.06
    ила
    -0.06
    -DD
    -0.06
    models
    -0.06
    æŁĶ软çļĦ
    -0.06
    POSITIVE LOGITS
    achi
    0.08
    thumb
    0.08
    ÐļТ
    0.07
    anty
    0.07
    Thumb
    0.07
    anca
    0.07
    ä¾ĭ
    0.07
    inna
    0.07
    éĴ¥
    0.07
    ordan
    0.07
    Activations Density 0.002%

    No Known Activations