© 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. 29025
    Prev
    Next
    INDEX
    Explanations

    agreement or consistency

    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
     banj
    -0.09
    orz
    -0.08
    äºĶé¢ľåħŃèī²çļĦ
    -0.08
    åı¯æ¢¦
    -0.08
    astre
    -0.08
    UnderTest
    -0.08
    大计
    -0.08
    éĺħè¯»æľ¬æĸĩåīį
    -0.08
    å±ŀäºİä½łçļĦ
    -0.08
    (Editor
    -0.08
    POSITIVE LOGITS
    符åIJĪ
    0.10
    åIJ»åIJĪ
    0.10
    สà¸Ńà¸Ķà¸Ħลà¹īà¸Ńà¸ĩ
    0.08
    缸符
    0.08
    åį°è¯ģ
    0.07
    agos
    0.07
    ago
    0.07
     ìĿ¼ì¹ĺ
    0.07
    bbe
    0.07
     predictions
    0.07
    Activations Density 0.027%

    No Known Activations