© 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. 20476
    Prev
    Next
    INDEX
    Explanations

    auxiliary, refers, any, range

    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
    _python
    -0.07
     történ
    -0.07
    над
    -0.07
    esen
    -0.07
    åĬĽæīĢèĥ½åıĬ
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
    entication
    -0.06
    ä¼ĺåĮĸçļĦ
    -0.06
    åĬ¨éĿĻ
    -0.06
    åıįæŃ£
    -0.06
    POSITIVE LOGITS
    asca
    0.07
    efa
    0.07
    æĢĿæºIJ
    0.07
    role
    0.07
    佬
    0.07
    çĻ½äºĨ
    0.07
    rito
    0.06
    gie
    0.06
    峡
    0.06
    æįº
    0.06
    Activations Density 0.017%

    No Known Activations