© 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. 33681
    Prev
    Next
    INDEX
    Explanations

    asking questions about possibility

    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
    åľ¨å¾Īå¤ļ
    -0.08
    å¾Ģå¾Ģ
    -0.08
    åĩłä¹İ
    -0.07
     usually
    -0.07
    éĢļ常
    -0.07
    éĢļ常éľĢè¦ģ
    -0.07
    åĩłä¹İæĺ¯
    -0.07
    à¹Īà¸Ńม
    -0.07
    å¾Īå¤ļéĹ®é¢ĺ
    -0.07
    åĭ¢
    -0.07
    POSITIVE LOGITS
    æľīè¿Ļæł·çļĦ
    0.11
     somewhere
    0.11
    æľīè¿Ļä¹Ī
    0.09
    è¿Ļæĸ¹éĿ¢çļĦ
    0.09
    çī¹å®ļçļĦ
    0.09
    æŁIJ个
    0.09
    kaus
    0.09
    æĺ¯è¿Ļæł·çļĦ
    0.08
    æŁIJåĢĭ
    0.08
    æŁIJç§į
    0.08
    Activations Density 0.090%

    No Known Activations