© 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. 12457
    Prev
    Next
    INDEX
    Explanations

    engine displacement or core count

    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
    广ä¹ī
    -0.07
    å½¢èī²
    -0.07
     Abram
    -0.06
    ä¸Ńæļij
    -0.06
    çĶ¨æľĢ
    -0.06
     unintended
    -0.06
    åįĬéĢĶ
    -0.06
     affirmative
    -0.06
    новÑĮ
    -0.06
    æıIJ示信æģ¯
    -0.06
    POSITIVE LOGITS
     upgraded
    0.09
     upgrade
    0.09
    upgrade
    0.08
     upgrading
    0.08
     upgrades
    0.08
    /native
    0.08
    cret
    0.08
    åįĩ级åĪ°
    0.08
     dual
    0.08
     decent
    0.08
    Activations Density 0.256%

    No Known Activations