© 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. 26733
    Prev
    Next
    INDEX
    Explanations

    USD pair

    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
    éĶĢ
    -0.06
     Palacio
    -0.06
    çıį
    -0.06
    æī¬éķ¿
    -0.06
    aglia
    -0.06
    зен
    -0.06
    ä¸Ģ件äºĭæĥħ
    -0.06
     Pfeffer
    -0.06
    大äºĨ
    -0.06
    chan
    -0.06
    POSITIVE LOGITS
    Pts
    0.08
    à¹Ģลืà¸Ń
    0.08
    ipun
    0.08
    bedingt
    0.08
    (Binary
    0.07
    dorf
    0.07
     cy
    0.07
    otka
    0.07
    poons
    0.07
    .watch
    0.07
    Activations Density 0.003%

    No Known Activations