© 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. 32412
    Prev
    Next
    INDEX
    Explanations

    equations with zero

    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
    andex
    -0.08
    人马
    -0.08
    ணà¯į
    -0.07
    armi
    -0.07
    fontsize
    -0.07
    éĥ¨åĪĨåĨħ容
    -0.07
    ATIC
    -0.07
    åŁº
    -0.07
    ResponseType
    -0.06
    ÃīR
    -0.06
    POSITIVE LOGITS
     either
    0.10
    either
    0.10
    ä¸įä¸Ģå®ļ
    0.09
     Ø¥Ùħا
    0.09
    æľªå¿ħ
    0.09
    è¦ģä¹Ī
    0.09
    并ä¸įæĦıåij³çĿĢ
    0.09
    Either
    0.08
     Either
    0.08
    ä½Ĩ并ä¸į
    0.08
    Activations Density 0.002%

    No Known Activations