© 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. 49212
    Prev
    Next
    INDEX
    Explanations

    syntax and structures

    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
    ools
    -0.07
    åįİåºŃ
    -0.07
    è¿Ľè¡Įæµĭè¯ķ
    -0.07
    éľĢè¦ģä»Ģä¹Ī
    -0.06
     vare
    -0.06
     Bens
    -0.06
    èĮĥåĽ´å¹¿
    -0.06
    æīķãģĦ
    -0.06
    èij©
    -0.06
     Scot
    -0.06
    POSITIVE LOGITS
    ince
    0.08
     undue
    0.08
    è¿ĩ度
    0.07
    éĩįåıł
    0.07
     duplicates
    0.07
    ók
    0.07
    adra
    0.07
    è´¨åľ°
    0.07
    اÙĤ
    0.07
     ì¤ijë³µ
    0.07
    Activations Density 0.005%

    No Known Activations