© 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. 3574
    Prev
    Next
    INDEX
    Explanations

    asymmetric transfer hydrogenation

    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
    /mock
    -0.06
    uhe
    -0.06
    vero
    -0.06
    ================================================================
    -0.06
    สัà¸ĩ
    -0.06
    æķĻçłĶ室
    -0.06
    uh
    -0.06
    äºĭåĬ¡æīĢ
    -0.06
     odom
    -0.06
     literature
    -0.06
    POSITIVE LOGITS
    ogos
    0.08
    halter
    0.07
    inking
    0.07
    antil
    0.07
    idding
    0.07
    inker
    0.07
    ablement
    0.07
    erman
    0.07
    (EFFECT
    0.07
    etros
    0.07
    Activations Density 0.005%

    No Known Activations