© 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. 3850
    Prev
    Next
    INDEX
    Explanations

    elements, lanthanides, gems, names, anomalies

    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
    åıĮæĸ¹å½ĵäºĭ人
    -0.07
    ä¹ħèĢĮ
    -0.07
    两项
    -0.07
    æīĢåIJij
    -0.06
    å½ĵäºĭ
    -0.06
    æĢĶ
    -0.06
    iked
    -0.06
    è¨Ģä¹ĭ
    -0.06
    cto
    -0.06
    èµ·åºĬ
    -0.06
    POSITIVE LOGITS
     anomal
    0.08
    æģ©
    0.08
    ardin
    0.08
    ä¸Ĭæ¦ľ
    0.08
    ä¼Łå¤§çļĦ
    0.08
    çļĦåIJįåŃĹ
    0.08
    -names
    0.08
     names
    0.08
    ä¸ĭä¸Ģ个
    0.07
    _next
    0.07
    Activations Density 0.001%

    No Known Activations