© 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. 58090
    Prev
    Next
    INDEX
    Explanations

    spectacular goals, latest trends, best model, cheap calls, creative marketing, clinical efficacy

    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
    AnimationFrame
    -0.07
     renc
    -0.07
    regor
    -0.07
    çĪ²
    -0.06
    éĤ¯
    -0.06
    å¹´å¤ļ
    -0.06
    Ø´ÙĬا
    -0.06
    }\"
    -0.06
    ://{
    -0.06
    ãģij
    -0.06
    POSITIVE LOGITS
     fry
    0.08
    ellig
    0.08
    åŃIJç±»
    0.08
    arts
    0.07
    潦
    0.07
    aw
    0.07
    undet
    0.07
    ç§įåħ»
    0.07
    roz
    0.07
    好åIJĹ
    0.07
    Activations Density 0.003%

    No Known Activations