© 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. 41251
    Prev
    Next
    INDEX
    Explanations

    code blocks with delimiters

    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
    izen
    -0.09
    orn
    -0.08
    rown
    -0.07
    رائ
    -0.07
    rib
    -0.07
     ('
    -0.07
    ieven
    -0.07
    ¨
    -0.06
    elten
    -0.06
    çĶ±åŃ¦æł¡
    -0.06
    POSITIVE LOGITS
    Ñģадка
    0.07
    jam
    0.07
    è§ģè¯ģ
    0.07
    ç»´å¥ĩ
    0.07
    noch
    0.07
    常驻
    0.07
    è¨Ģ
    0.07
    ç»ĵæŀĦæĢ§æĶ¹éĿ©
    0.07
    hoff
    0.06
    çĸ¤
    0.06
    Activations Density 0.139%

    No Known Activations