© 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. 12683
    Prev
    Next
    INDEX
    Explanations

    gradient descent

    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
    orada
    -0.08
    idon
    -0.08
    åħīåįİ
    -0.08
    大éĩıçļĦ
    -0.08
    fum
    -0.07
    ereien
    -0.07
    ä¸įå¤ļçļĦ
    -0.07
    ukup
    -0.07
    ercul
    -0.07
    arki
    -0.07
    POSITIVE LOGITS
    omar
    0.08
    å¾Ļ
    0.08
    çĹĽ
    0.07
    hog
    0.07
    sor
    0.07
    åľºå¤ĸ
    0.07
     Appalach
    0.07
    à°¤à±į
    0.07
    urt
    0.07
     directions
    0.07
    Activations Density 0.002%

    No Known Activations