© 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. 40508
    Prev
    Next
    INDEX
    Explanations

    largest/most of

    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
    æĢªä¸įå¾Ĺ
    -0.07
    allas
    -0.07
    人影
    -0.07
    ahir
    -0.07
    àµĩà´¶
    -0.07
    ä½ľçĶ»
    -0.07
    wal
    -0.06
    cÄĥ
    -0.06
    egram
    -0.06
    ibur
    -0.06
    POSITIVE LOGITS
     among
    0.10
     amongst
    0.08
    among
    0.08
    влека
    0.08
     spoÅĽród
    0.07
    æĹłèĻij
    0.07
     Among
    0.07
    çľ¾å¤ļ
    0.07
    ä»»ä¸Ģ
    0.07
    æĹłæĤĶ
    0.07
    Activations Density 0.179%

    No Known Activations