© 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. 63612
    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
    æķ£
    -0.08
    asse
    -0.08
    ä¸įèĢIJçĥ¦
    -0.07
    ç¨
    -0.07
    å¸Ĥåľº
    -0.06
    ÃŃ
    -0.06
    马éĩĮ
    -0.06
    æ½ĩæ¹ĺ
    -0.06
    IFE
    -0.06
    ihe
    -0.06
    POSITIVE LOGITS
    blia
    0.08
    åı¤å±ĭ
    0.07
    éģĵåıĭ
    0.07
    æľĢæĸ°è¯Ħ论
    0.07
    klar
    0.07
    ÑĤай
    0.07
    staan
    0.07
    ().__
    0.07
    edly
    0.07
    à¸Ĭà¸Ļ
    0.07
    Activations Density 0.000%

    No Known Activations