© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20397
    Prev
    Next
    INDEX
    Explanations

    quantity measurement

    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
    èĢĥ
    -0.07
    好æĸĩ
    -0.06
    åľ¨éĤ£éĩĮ
    -0.06
    絶
    -0.06
    Æ°á»Ľc
    -0.06
    oid
    -0.06
    åı¯ä»¥åĪ©çĶ¨
    -0.06
    ربع
    -0.06
    ero
    -0.06
    eras
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.09
    pies
    0.07
    åİŁä»¶åıĬ
    0.07
    piring
    0.07
    LLU
    0.07
    ponsible
    0.07
    å°Ķæĸ¯
    0.07
    hyl
    0.07
    æĬ¥åIJįæŶ
    0.07
    entai
    0.07
    Activations Density 0.067%

    No Known Activations