© 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. 40237
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    cik
    -0.09
    %x
    -0.07
    edal
    -0.07
    ä¼¼éĶ¦
    -0.07
    uit
    -0.07
    èĵ¦
    -0.07
    æľ«å¹´
    -0.06
    aso
    -0.06
    uits
    -0.06
    axter
    -0.06
    POSITIVE LOGITS
    olut
    0.07
    ç±³äºļ
    0.07
    ç»´äºļ
    0.07
     <<-
    0.07
    è¿ĺä¸įèĥ½
    0.07
    åľ°çĵľ
    0.07
     ReturnType
    0.07
    æĢĴ
    0.07
    iard
    0.07
    parameter
    0.07
    Activations Density 0.000%

    No Known Activations