© 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. 8114
    Prev
    Next
    INDEX
    Explanations

    delay after wished

    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
     Conf
    -0.07
    å¹´å¹´
    -0.07
     ga
    -0.07
    .spring
    -0.07
     g
    -0.07
    ELLI
    -0.06
     conf
    -0.06
     zej
    -0.06
    _CONF
    -0.06
    æĻ®æ³ķ
    -0.06
    POSITIVE LOGITS
    åľ¨åIJĦ个
    0.09
    ãģļãģ¤
    0.09
    Įĵ
    0.08
     multidiscipl
    0.08
    åħ¨æĸ¹ä½į
    0.08
    ifar
    0.08
    iment
    0.08
    ëĶĶ
    0.07
    åıįä¹ĭ
    0.07
    éŃ
    0.07
    Activations Density 0.800%

    No Known Activations