© 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. 46128
    Prev
    Next
    INDEX
    Explanations

    chemical followed by a process

    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
    ung
    -0.08
    u
    -0.08
    ductory
    -0.08
    shire
    -0.08
    ee
    -0.07
    Ñı
    -0.07
    gether
    -0.07
    ekom
    -0.07
    ed
    -0.07
    äter
    -0.06
    POSITIVE LOGITS
    ised
    0.10
    ifornia
    0.09
    å·¥ä¸ļåĩºçīĪ社
    0.09
    ypse
    0.09
    igned
    0.08
     halnya
    0.08
    umbre
    0.08
    leston
    0.08
    à¸Ķีย
    0.08
    nown
    0.08
    Activations Density 0.023%

    No Known Activations