© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30327
    Prev
    Next
    INDEX
    Explanations

    is followed by explanation

    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
     Legislat
    -0.09
    uš
    -0.08
    Ø´ÛĮÙĨ
    -0.08
    ognito
    -0.08
    olumn
    -0.08
    irurg
    -0.08
    åı¤å±ĭ
    -0.08
    PROTO
    -0.08
    æĤ¨å½ĵåīįçļĦä½įç½®
    -0.08
    ByVersion
    -0.08
    POSITIVE LOGITS
    åŁºäºİ
    0.07
     consistent
    0.07
     based
    0.07
    é¢Ĺ
    0.07
    æºIJäºİ
    0.06
     P
    0.06
     backed
    0.06
    ä½ĵçİ°äºĨ
    0.06
    çݰ象
    0.06
     due
    0.06
    Activations Density 0.090%

    No Known Activations