© 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. 56730
    Prev
    Next
    INDEX
    Explanations

    agreeing to terms

    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
    imar
    -0.06
     Rocha
    -0.06
    erts
    -0.06
     kar
    -0.06
    éķľ
    -0.06
    _TURN
    -0.06
    èĪĨ
    -0.06
    º
    -0.06
     e
    -0.06
    unt
    -0.06
    POSITIVE LOGITS
    符åIJĪ
    0.14
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.13
    è¿Ŀåıįä¸Ĭè¿°
    0.13
    ä¸¥æł¼æĮīçħ§
    0.13
    å¿ħ须符åIJĪ
    0.12
    ä¾Ŀçħ§
    0.12
     conformément
    0.11
    該å½ĵ
    0.10
    åľ¨ä¸Ĭè¿°
    0.10
    ä¸į符åIJĪ
    0.10
    Activations Density 0.402%

    No Known Activations