© 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. 50629
    Prev
    Next
    INDEX
    Explanations

    code configuration

    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
    endem
    -0.08
    ientos
    -0.08
    adora
    -0.07
    ardini
    -0.07
    czÄħ
    -0.07
    ÙĨدÙĩ
    -0.07
     levering
    -0.07
    èĿł
    -0.07
    enders
    -0.07
    apura
    -0.07
    POSITIVE LOGITS
     MOTOR
    0.08
    ouw
    0.08
    rasil
    0.07
    æŀ
    0.07
     motor
    0.07
    /welcome
    0.07
    ç©Ĺ
    0.07
    å®ŀè¯ģ
    0.07
     Motor
    0.07
    书éĿ¢å½¢å¼ı
    0.06
    Activations Density 0.001%

    No Known Activations