© 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. 50600
    Prev
    Next
    INDEX
    Explanations

    literary movement, writers, poets

    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
    åı£ä»¤
    -0.09
    ç§ijçłĶ
    -0.08
    engk
    -0.07
     unarmed
    -0.07
     Protocol
    -0.07
    èĤīçľ¼
    -0.06
    ãĥĻãĥ¼ãĥĪ
    -0.06
     Kinect
    -0.06
    fredo
    -0.06
     protocol
    -0.06
    POSITIVE LOGITS
    æĬĴæĥħ
    0.13
    åĪĽä½ľ
    0.13
     prose
    0.13
    ä»ĸçļĦä½ľåĵģ
    0.12
     stylist
    0.12
    åĪĽä½ľçļĦ
    0.11
    ä½ľåĵģ
    0.11
     literary
    0.11
    ä½ľåĵģä¸Ń
    0.11
     anthology
    0.11
    Activations Density 0.324%

    No Known Activations