© 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. 3760
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
     decisive
    -0.07
    اÙĨÙĬ
    -0.07
    .instance
    -0.06
    Bah
    -0.06
    izz
    -0.06
    dav
    -0.06
    uj
    -0.06
    èį
    -0.06
     Sap
    -0.06
    è£ģ
    -0.06
    POSITIVE LOGITS
    áĥ§áĥĿ
    0.08
    volv
    0.08
    LocalStorage
    0.07
    zusch
    0.07
    åIJįåĮ»
    0.07
    Ñĥп
    0.07
    åŃ¢
    0.07
    zia
    0.07
    ç»Ŀåľ°
    0.07
    trar
    0.07
    Activations Density 0.015%

    No Known Activations