© 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. 55398
    Prev
    Next
    INDEX
    Explanations

    PWN or ECT

    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
    ļľ
    -0.08
    urname
    -0.08
    ¾
    -0.07
    åIJĪåIJĮçºłçº·ä¸Ģæ¡Ī
    -0.07
    fé
    -0.07
    人å¿ĥ
    -0.07
    ÑĢег
    -0.07
    èķĥ
    -0.07
    çļĦå¿ĥ声
    -0.07
    è¨Ģä¹ĭ
    -0.07
    POSITIVE LOGITS
    å¦ĤèĬ±
    0.06
    ilib
    0.06
    å¦Ĥ对
    0.06
    etim
    0.06
     pes
    0.06
    .Stretch
    0.05
     Pern
    0.05
    pst
    0.05
    Obj
    0.05
    æĢİæł·åģļ
    0.05
    Activations Density 0.161%

    No Known Activations