© 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. 38159
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    áĬĵ
    -0.06
    zell
    -0.06
    èĨĬ
    -0.06
    ÃijA
    -0.06
    mq
    -0.06
    åİ»çļ®
    -0.06
     nämlich
    -0.06
    èĬ
    -0.06
    éĵ¶æ²³
    -0.05
    ank
    -0.05
    POSITIVE LOGITS
    <tool_response>
    0.08
    ä¸Ģåı·
    0.08
    getragen
    0.07
    åIJijè®°èĢħ
    0.07
    ongsTo
    0.07
    çļĦçĹħ
    0.07
     itd
    0.07
    alink
    0.07
    _callbacks
    0.07
    æ³ķçŃī
    0.07
    Activations Density 0.181%

    No Known Activations