© 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. 13773
    Prev
    Next
    INDEX
    Explanations

    repeatedly, side, speed, early, stable

    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
    åIJĥäºĨ
    -0.09
    anan
    -0.09
    åľ¨çİ©
    -0.08
    ä½ıçļĦ
    -0.08
    urg
    -0.08
    /build
    -0.08
    ä¸İçłĶ究
    -0.08
    Õ¡Õ½
    -0.08
    åģľäºĨ
    -0.08
    upi
    -0.08
    POSITIVE LOGITS
    ately
    0.08
    åľ°è¿Ľè¡Į
    0.07
    æĸ¹å¼ıè¿Ľè¡Į
    0.07
    çĤ¹è¿Ľè¡Į
    0.07
    å¼ı
    0.07
    è¿Ľè¡Į
    0.07
    管çIJĨçŃī
    0.07
    管çIJĨæīĢ
    0.07
    æĸ¹æ³ķè¿Ľè¡Į
    0.06
    quential
    0.06
    Activations Density 0.045%

    No Known Activations