© 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. 8920
    Prev
    Next
    INDEX
    Explanations

    topics and guidance

    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
    akas
    -0.07
     Rudd
    -0.07
    åIJĬ
    -0.06
    èĩªå·±çļĦ人
    -0.06
    اج
    -0.06
    çī¹å¤§
    -0.06
    æ²ĸ
    -0.06
     characterization
    -0.06
    为äºĨç¡®ä¿Ŀ
    -0.06
    åħ³äºİåĬłå¼º
    -0.06
    POSITIVE LOGITS
    åħ·
    0.07
     domani
    0.07
    rieve
    0.07
     tomorrow
    0.07
    serter
    0.07
    åĬ©åĬĽ
    0.07
    ADR
    0.07
    Src
    0.07
    çļĦä¸įæĺ¯
    0.07
    agic
    0.07
    Activations Density 0.007%

    No Known Activations