© 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. 33775
    Prev
    Next
    INDEX
    Explanations

    Ninth Circuit

    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
    天å¤ĸ
    -0.08
    icle
    -0.08
    wap
    -0.08
    imoto
    -0.08
    cken
    -0.07
    ettori
    -0.07
    à¥įरà¥Ģ
    -0.07
    ;height
    -0.07
    ocities
    -0.07
    å·¥ä½ľåĬ¨æĢģ
    -0.07
    POSITIVE LOGITS
    èĢĮ为
    0.07
    h
    0.06
     conclude
    0.06
    nit
    0.06
     stip
    0.06
    åĨħ容为
    0.06
    æľŁä¸º
    0.06
    inte
    0.06
    çıŃçļĦ
    0.06
     toned
    0.06
    Activations Density 0.022%

    No Known Activations