© 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. 22149
    Prev
    Next
    INDEX
    Explanations

    frozen_string_literal

    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
    opak
    -0.09
    åįģä¹Ŀç«ł
    -0.08
    æī§è¡Įèij£äºĭ
    -0.08
    é¹Ĭ
    -0.08
    unction
    -0.08
    èµĦæł¼çļĦ
    -0.08
    æĢ»é¢ĿçļĦ
    -0.08
    elan
    -0.08
    ascript
    -0.08
    :title
    -0.08
    POSITIVE LOGITS
    --
    0.07
    2
    0.06
    3
    0.06
     NOTA
    0.06
    åıĹ
    0.06
     \"
    0.05
    å¤ļç±³
    0.05
    ieren
    0.05
    ä¸Ń
    0.05
    ä¸ĭéĿ¢çļĦ
    0.05
    Activations Density 0.006%

    No Known Activations