© 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. 40137
    Prev
    Next
    INDEX
    Explanations

    residential school

    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
    ä¸Ģéĺµéĺµ
    -0.08
    æĭ¾
    -0.08
    asseur
    -0.07
    ä¹ħèĢĮ
    -0.07
    ì§ģ
    -0.07
    ×ķ×ŀר
    -0.07
    wann
    -0.07
    новиÑĩ
    -0.07
    缸å½ĵ
    -0.07
    åĪĨåĮĸ
    -0.07
    POSITIVE LOGITS
    zien
    0.07
    æĻŁ
    0.07
    人åı¯ä»¥
    0.06
    éĤ£è¾¹
    0.06
    æľĢåIJİä¸Ģ个
    0.06
    ah
    0.06
    ch
    0.06
     Regarding
    0.06
    ush
    0.06
     Prescott
    0.06
    Activations Density 0.037%

    No Known Activations