© 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. 21763
    Prev
    Next
    INDEX
    Explanations

    existence of some

    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
    æľīä»Ģä¹Ī
    -0.09
    åı¯èĥ½æĢ§
    -0.07
    aupt
    -0.07
    æľīåķ¥
    -0.07
    è¯ķåĽ¾
    -0.06
    åħ¸åŀĭçļĦ
    -0.06
    主è¦ģ
    -0.06
     бÑĥдÑĤо
    -0.06
     warmth
    -0.06
    ==
    -0.06
    POSITIVE LOGITS
    çİĭ大
    0.08
    ikka
    0.08
    èĩ³å°ijåľ¨
    0.08
    ä¹ĭ忧
    0.08
    å©·å©·
    0.08
    å¿ħãģļ
    0.08
     ÙĪÙĦÙĪ
    0.08
    åħĪæĿ¥
    0.07
     plenty
    0.07
    ÃŃc
    0.07
    Activations Density 0.037%

    No Known Activations