© 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. 29920
    Prev
    Next
    INDEX
    Explanations

    correct size, spacing, numbers

    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
    åĩĨ
    -0.08
    æĪĸèĢħ
    -0.07
    æĪĸ
    -0.07
    lesi
    -0.07
    æĪĸèĢħåħ¶ä»ĸ
    -0.07
    æĪijåIJ§
    -0.07
    æĪĸåħ¶ä»ĸ
    -0.07
    æĪĸèĢħæľī
    -0.07
    åijĹ
    -0.07
    аÑĤелÑĮÑģÑĤва
    -0.07
    POSITIVE LOGITS
     correctly
    0.12
    æŃ£ç¡®åľ°
    0.09
     correct
    0.09
     correctamente
    0.09
    å·¥ä½ľçļĦåIJĮæŶ
    0.09
    æĺ¯æŃ£ç¡®çļĦ
    0.08
     Äijúng
    0.08
    æĹłè¯¯
    0.08
    åºĶæľīçļĦ
    0.08
    该æľīçļĦ
    0.08
    Activations Density 0.034%

    No Known Activations