© 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. 60882
    Prev
    Next
    INDEX
    Explanations

    Germanic languages

    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
    åħ¼
    -0.08
    dup
    -0.07
    lap
    -0.06
    æĥŃ
    -0.06
    åij±åij±
    -0.06
    uden
    -0.06
    æĶ¾
    -0.06
    yle
    -0.06
    ugt
    -0.06
    schw
    -0.06
    POSITIVE LOGITS
    ç³»åĪĹ
    0.17
    ç±»
    0.17
    ç³»åĪĹçļĦ
    0.15
    ç±»çŃī
    0.14
    é¡ŀ
    0.14
     ê³ĦìĹ´
    0.14
     series
    0.13
    ç±»çļĦ
    0.13
    ç±»ä¸ĵä¸ļ
    0.13
    ä¸Ģç±»
    0.13
    Activations Density 0.598%

    No Known Activations