© 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. 63667
    Prev
    Next
    INDEX
    Explanations

    legal citation numbers

    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
    é´
    -0.06
    /DD
    -0.06
    éħ¸çĽIJ
    -0.06
    èµĦä¿¡
    -0.06
     Dungeons
    -0.06
    ä¸Ģ个åı«
    -0.06
    æĿ¡ä»¶æĺ¯
    -0.06
     Leggi
    -0.06
    ickt
    -0.06
    è±
    -0.06
    POSITIVE LOGITS
    alin
    0.08
    ubin
    0.08
    춤
    0.07
    follow
    0.07
    wh
    0.07
    èįīæł¹
    0.07
    òng
    0.07
    <|box_end|>
    0.07
    меÑĢ
    0.07
    isa
    0.07
    Activations Density 0.092%

    No Known Activations