© 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. 39585
    Prev
    Next
    INDEX
    Explanations

    Activity B, Cara Smelter, oneTimeTask, Five facts

    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
    ÐĵУ
    -0.08
    eldon
    -0.07
    wy
    -0.06
     Justi
    -0.06
    æĽ´æĸ°æŶéĹ´
    -0.06
    ç¼Ń
    -0.06
    éļħ
    -0.06
    wald
    -0.06
    overe
    -0.06
    usra
    -0.06
    POSITIVE LOGITS
    ³³³³³³³
    0.07
    ³³³³³³³³
    0.07
    ä½łæĺ¯æĪijçļĦ
    0.07
    ³³³³
    0.07
    ³³³
    0.06
    isis
    0.06
    inas
    0.06
     Epstein
    0.06
    yam
    0.06
    lob
    0.06
    Activations Density 0.405%

    No Known Activations