© 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. 49017
    Prev
    Next
    INDEX
    Explanations

    pull updates

    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
    iveness
    -0.08
    ember
    -0.08
    brio
    -0.07
    egers
    -0.07
    inoa
    -0.07
    unken
    -0.07
    åĪĨ离åĻ¨
    -0.06
    åľ¨ä»ĬåIJİçļĦå·¥ä½ľä¸Ń
    -0.06
    неÑĢа
    -0.06
    åŃIJäºĨ
    -0.06
    POSITIVE LOGITS
    ulk
    0.08
    _DECLARE
    0.07
    åĨįä»İ
    0.07
    auge
    0.07
    ãģĨãģ¤
    0.07
     thô
    0.07
    azy
    0.07
    rique
    0.07
    jal
    0.07
    è¿ĩå¢ĥ
    0.07
    Activations Density 0.003%

    No Known Activations