© 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. 30465
    Prev
    Next
    INDEX
    Explanations

    Generated, produced, derived, created

    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
     Garr
    -0.07
    izen
    -0.07
    à¹Ģà¸Ĺศ
    -0.07
    -Length
    -0.07
    PerPage
    -0.06
    ä¸İæĸ¹æ³ķ
    -0.06
    çļĦåĩºçİ°
    -0.06
    ç¼Ī
    -0.06
    Docs
    -0.06
    ouser
    -0.06
    POSITIVE LOGITS
    æīĢå¾Ĺ
    0.15
    -generated
    0.14
    -produced
    0.13
    å¾ĹåĪ°çļĦ
    0.12
    -derived
    0.12
    åIJİçļĦ
    0.12
    å¾ĹæĿ¥çļĦ
    0.12
    -created
    0.11
    ç»ĵæŀľ
    0.11
    æĪIJæŀľ
    0.10
    Activations Density 0.362%

    No Known Activations