© 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. 58582
    Prev
    Next
    INDEX
    Explanations

    i.e

    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
    ness
    -0.09
    ÙĨÙĬات
    -0.07
    à¸ĩ
    -0.07
    ниÑĨÑĮ
    -0.07
    à´¤àµįà´°
    -0.07
    лÑĮев
    -0.07
    маÑħ
    -0.07
    ب
    -0.07
    ниÑĨа
    -0.07
    ÑĤий
    -0.06
    POSITIVE LOGITS
    0.11
    ently
    0.10
    ä¸Ģæĸij
    0.09
    ï¸İ
    0.09
    .,
    0.09
    ़
    0.08
    ally
    0.08
    åĦ¿çļĦ
    0.08
    สà¹Į
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.08
    Activations Density 0.018%

    No Known Activations