© 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. 31905
    Prev
    Next
    INDEX
    Explanations

    physical objects and concepts

    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
     zm
    -0.06
    å¼łæµ·
    -0.06
    วาà¸Ļ
    -0.06
    èĩ£
    -0.06
    å¾ĺ
    -0.06
    ç«ĭå¼ı
    -0.05
    å¸Į
    -0.05
    EventManager
    -0.05
    âī¯
    -0.05
    .parseInt
    -0.05
    POSITIVE LOGITS
    æľ¬èº«
    0.09
    åıĬåħ¶
    0.09
    æľ¬èº«çļĦ
    0.08
     itself
    0.08
    åıĬéħį件
    0.08
     samot
    0.08
    еÑģÑĤа
    0.07
    åıĬéħįå¥Ĺ
    0.07
     fata
    0.07
    ÛķÚ©
    0.07
    Activations Density 0.270%

    No Known Activations