© 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. 45366
    Prev
    Next
    INDEX
    Explanations

    method or technique

    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
    aldo
    -0.08
    bjerg
    -0.07
     Needed
    -0.07
    Needed
    -0.07
     rentrée
    -0.07
    annon
    -0.06
    åıĬæľīåħ³
    -0.06
    λαν
    -0.06
    ampi
    -0.06
    æ´¥
    -0.06
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹æ³ķ
    0.15
    è¿Ļç§įæĸ¹å¼ı
    0.13
    ä¼ĺçĤ¹æĺ¯
    0.13
    è¿Ļç§įåģļæ³ķ
    0.11
    çļĦä¼ĺçĤ¹
    0.11
    缺çĤ¹æĺ¯
    0.11
    第äºĮç§į
    0.10
     disadvantages
    0.10
    第ä¸īç§į
    0.10
    è¿Ļ个æĸ¹æ³ķ
    0.10
    Activations Density 0.469%

    No Known Activations