© 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. 47852
    Prev
    Next
    INDEX
    Explanations

    complexity and algorithms

    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
     Angus
    -0.07
    antil
    -0.06
     Annex
    -0.06
     annex
    -0.06
    ัà¸ģ
    -0.06
    estia
    -0.06
    å¥½äºĽ
    -0.06
    enant
    -0.06
     sake
    -0.06
    象çīĻ
    -0.06
    POSITIVE LOGITS
    agina
    0.09
     revan
    0.08
    çĭ¬ç«ĭ
    0.07
    ÑģлÑĸ
    0.07
    alar
    0.07
    Ïģιθ
    0.07
    udah
    0.07
    raid
    0.07
    gpu
    0.07
    izen
    0.07
    Activations Density 0.006%

    No Known Activations