© 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. 57598
    Prev
    Next
    INDEX
    Explanations

    launching

    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
    ore
    -0.08
    ernen
    -0.07
    orer
    -0.07
    azioni
    -0.07
    çªŁ
    -0.06
    lier
    -0.06
    ئا
    -0.06
    osis
    -0.06
    iddy
    -0.06
    lice
    -0.06
    POSITIVE LOGITS
     khá»ıi
    0.11
    arote
    0.09
    åľ¨åį³
    0.09
    uard
    0.09
    =start
    0.09
    à¸Ńà¸Ńà¸ģà¸Īาà¸ģ
    0.08
    ä¼Ĭå§ĭ
    0.08
    èµ·é£ŀ
    0.08
    à¸Ĺีà¹Ģà¸Ķียว
    0.08
    ä¸įåĩºåİ»
    0.08
    Activations Density 0.027%

    No Known Activations