© 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. 47760
    Prev
    Next
    INDEX
    Explanations

    and show

    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
    rench
    -0.09
    æīį被
    -0.08
    semble
    -0.08
     geworden
    -0.08
    ëĵł
    -0.08
    ä¹Łä¸įä¸Ģå®ļ
    -0.08
    亦çĦ¶
    -0.07
    被åıijçİ°
    -0.07
    ÑĪли
    -0.07
    erse
    -0.07
    POSITIVE LOGITS
    并å°Ĩåħ¶
    0.11
    并ç»ĵåIJĪ
    0.08
    åıĬåħ¶
    0.08
    并注æĦı
    0.08
     noting
    0.08
    并确ä¿Ŀ
    0.08
    并éĢļè¿ĩ
    0.08
    并
    0.07
    以åıĬ
    0.07
    并æĬĬ
    0.07
    Activations Density 0.224%

    No Known Activations