© 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. 30865
    Prev
    Next
    INDEX
    Explanations

    oxidation

    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
    çī¹åĭĴ
    -0.07
    anel
    -0.07
    تÙĪÙĨ
    -0.07
    èĽĨ
    -0.07
    丸
    -0.07
    pite
    -0.06
    hattan
    -0.06
    ingroup
    -0.06
    à¸łà¸²à¸ŀ
    -0.06
    æ²īæµ®
    -0.06
    POSITIVE LOGITS
    emper
    0.08
    ionic
    0.08
     nhẹ
    0.08
    ences
    0.08
    éré
    0.08
    çĤ¹æ»´
    0.08
    ions
    0.07
    ypes
    0.07
    à¹Ģสม
    0.07
    ly
    0.07
    Activations Density 0.005%

    No Known Activations