© 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. 55445
    Prev
    Next
    INDEX
    Explanations

    in the night

    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
    å¿Ĺ强
    -0.11
    æıīäºĨ
    -0.10
    çķ¶ä¸ĭ
    -0.09
     ÐŀÑģно
    -0.09
    mux
    -0.09
    .Excel
    -0.09
     изнаÑĩалÑĮно
    -0.09
    isko
    -0.08
    ligh
    -0.08
    ä¹ĭåĪĥ
    -0.08
    POSITIVE LOGITS
    âĢ¦âĢ¦
    0.10
     âĢ¦
    0.10
    0.08
    _
    0.08
    âĢ¦
    0.07
    éĤ£æł·
    0.07
    ___
    0.07
     Wh
    0.07
    —
    0.07
    ç«Ł
    0.06
    Activations Density 0.005%

    No Known Activations