© 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. 7519
    Prev
    Next
    INDEX
    Explanations

    verification and checking

    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
    çĤºèĩªå·±
    -0.08
    çĦ¶æĺ¯
    -0.08
    èĩªè¡ĮæıIJä¾Ľ
    -0.08
     conh
    -0.07
    iffe
    -0.07
    ledo
    -0.07
    äºĶé¢ľåħŃèī²çļĦ
    -0.07
    èħ¾èħ¾
    -0.07
    $num
    -0.07
    ä¿¡çĶ¨ä¿¡æģ¯
    -0.07
    POSITIVE LOGITS
     by
    0.08
    alt
    0.07
     through
    0.07
     via
    0.07
    het
    0.07
    through
    0.06
     Pob
    0.06
    by
    0.06
    çļĦè¯Ŀ
    0.06
    ï¼ļ
    0.06
    Activations Density 0.003%

    No Known Activations