© 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. 11484
    Prev
    Next
    INDEX
    Explanations

    negative, positive, or 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
    olas
    -0.09
    upy
    -0.08
    .ylim
    -0.07
    esos
    -0.07
    åľŁè±ª
    -0.07
    preserve
    -0.07
    æļĩ
    -0.07
    ungk
    -0.07
    åį´ä¸Ģ缴
    -0.07
    ä¸Ģè·ĥ
    -0.07
    POSITIVE LOGITS
    bane
    0.07
    æķħ人
    0.07
    çĽ¸å¯¹äºİ
    0.07
    족
    0.07
    æģ¶
    0.07
     ÙģعÙĦÙĬ
    0.07
    ç¡®å®ŀ
    0.06
     Sheridan
    0.06
    確實
    0.06
    æĸĩåŃĹ
    0.06
    Activations Density 0.003%

    No Known Activations