© 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. 21525
    Prev
    Next
    INDEX
    Explanations

    for or with

    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
    æ·ij
    -0.07
    æĬī
    -0.06
    ioc
    -0.06
     chì
    -0.06
    åIJĮéģĵ
    -0.06
    ذاب
    -0.06
    ãģĭãĤı
    -0.06
    è´£ç¼ĸ
    -0.06
     напÑĢоÑĤив
    -0.06
    路西
    -0.06
    POSITIVE LOGITS
    æĪijåIJĹ
    0.09
    sofar
    0.09
     whichever
    0.09
     lắm
    0.09
    ä½Ĩå½ĵ
    0.08
    ä½Ĩæĺ¯å½ĵ
    0.08
     both
    0.08
     Cases
    0.07
     cases
    0.07
     olyan
    0.07
    Activations Density 0.301%

    No Known Activations