© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17861
    Prev
    Next
    INDEX
    Explanations

    about followed by words

    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
    ÑĤен
    -0.09
    以赴
    -0.09
    ãĤĪãģĨãģ«ãģªãģ£ãģ¦
    -0.08
    lessness
    -0.08
    راÙĨ
    -0.08
    аÑĢÑĤ
    -0.08
    mons
    -0.08
    éĤ£æĺ¯åĽłä¸º
    -0.08
    ijken
    -0.08
    acro
    -0.08
    POSITIVE LOGITS
    è¿Ļæĸ¹éĿ¢çļĦ
    0.09
    “
    0.08
    eve
    0.08
    ness
    0.08
    e
    0.07
    ä»Ģä¹ĪçļĦ
    0.07
    ht
    0.07
    y
    0.07
    æĪijæĿ¥è¯´
    0.07
    æѤäºĭ
    0.07
    Activations Density 0.001%

    No Known Activations