© 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. 21145
    Prev
    Next
    INDEX
    Explanations

    last time or last update

    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
    ials
    -0.09
    å¹´å§ĭ
    -0.08
    çł´äºĨ
    -0.08
    .ReadOnly
    -0.08
     erken
    -0.08
    æĹ©æľŁçļĦ
    -0.08
     nantinya
    -0.08
    第ä¸Ģæī¹
    -0.07
    çļĦæ°ijæĹı
    -0.07
    第ä¸Ģå¹´
    -0.07
    POSITIVE LOGITS
    last
    0.11
    -last
    0.11
    (last
    0.11
    ä¸Ĭä¸Ģ次
    0.11
     last
    0.11
    [last
    0.10
    recent
    0.10
     getLast
    0.10
     recent
    0.10
    æľĢè¿ij
    0.09
    Activations Density 0.117%

    No Known Activations