© 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. 8970
    Prev
    Next
    INDEX
    Explanations

    only when / after / 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
    steller
    -0.07
    ë¹Ī
    -0.07
    åIJĪåIJĮæŶ
    -0.07
     elsewhere
    -0.07
    ìĩĦ
    -0.07
    èĻ½çĦ¶åľ¨
    -0.07
    ÙħاÙĩ
    -0.07
     sendiri
    -0.07
    lom
    -0.07
    orse
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·æīįèĥ½
    0.11
    ÙĮ
    0.08
    åIJİæīįèĥ½
    0.08
    çļĦ人ä¼ļ
    0.08
    åĽłç´łå½±åĵį
    0.08
    åIJİæĸ¹åı¯
    0.08
    ÑģÑĮ
    0.07
    éĥ¨åĪĨç»ĦæĪIJ
    0.07
    Ùĭ
    0.07
     mattered
    0.07
    Activations Density 0.050%

    No Known Activations