© 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. 63599
    Prev
    Next
    INDEX
    Explanations

    polynomials and sequences

    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
    äºĮ人çļĦ
    -0.07
    iance
    -0.07
    åIJĪ
    -0.07
    åIJĪä½ĵ
    -0.07
    à¯Ĭ
    -0.06
    inin
    -0.06
    åı¯çŁ¥
    -0.06
    erschaft
    -0.06
    好å¥ĩå¿ĥ
    -0.06
    ã
    -0.06
    POSITIVE LOGITS
    ä¸İåħ¶å®ĥ
    0.09
    klik
    0.08
    plice
    0.08
    æ§Ľ
    0.08
    åįĥç§ĭ
    0.08
     Stout
    0.08
    ä¸İåħ¶ä»ĸ
    0.08
    ãģ©ãģĵãĤį
    0.08
     ÑģоÑģ
    0.07
     kaut
    0.07
    Activations Density 0.009%

    No Known Activations