© 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. 1789
    Prev
    Next
    INDEX
    Explanations

    how from Russian/Spanish/Portuguese

    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
    tle
    -0.09
    -0.09
    ัà¸ĩ
    -0.08
    schritt
    -0.08
    èĢĮå¤į
    -0.08
    uggle
    -0.08
    nik
    -0.08
    ivers
    -0.08
    اÛĮØ´
    -0.08
    мок
    -0.08
    POSITIVE LOGITS
     halnya
    0.11
    soever
    0.11
    vente
    0.10
     Ñĥгодно
    0.10
    quiera
    0.10
    ÑĤÑĥÑģ
    0.08
    opup
    0.08
     бÑĥдÑĤо
    0.08
    ой
    0.07
    ledge
    0.07
    Activations Density 0.038%

    No Known Activations