© 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. 15932
    Prev
    Next
    INDEX
    Explanations

    comparison with false

    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
    åŁ
    -0.07
    å¼ĢåĪ°
    -0.07
    agno
    -0.07
    okit
    -0.07
    olni
    -0.07
    antin
    -0.07
    æ´»åĬ¨è¿ĩç¨ĭ
    -0.07
    enton
    -0.07
     quis
    -0.07
    POSITIVE LOGITS
    ÑīеÑĤ
    0.08
    iculty
    0.07
    uesta
    0.07
    μβ
    0.07
    SG
    0.07
     behavior
    0.07
    ãģ£ãģĵ
    0.07
    inj
    0.06
     Behavior
    0.06
    é¢ĦæľŁ
    0.06
    Activations Density 0.001%

    No Known Activations