© 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. 8485
    Prev
    Next
    INDEX
    Explanations

    rounds and quarterfinals

    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
    GBT
    -0.07
    åĪ°å¤´
    -0.07
    å¤©çľ¼æŁ¥
    -0.07
    ç½ijæł¡
    -0.07
    zej
    -0.07
    enario
    -0.07
    åĪ°ä½į
    -0.07
    stärke
    -0.07
    åĪ°æĻļ
    -0.07
    ÑĨа
    -0.07
    POSITIVE LOGITS
    ju
    0.07
    ادÙħ
    0.07
    .gs
    0.07
    AN
    0.07
    yw
    0.07
     Natal
    0.06
    (py
    0.06
    omini
    0.06
    bang
    0.06
    olim
    0.06
    Activations Density 0.004%

    No Known Activations