© 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. 10278
    Prev
    Next
    INDEX
    Explanations

    word beginnings

    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
    æīĢ欲
    -0.08
     cÃłng
    -0.06
    åķ
    -0.06
    -between
    -0.06
     Aussch
    -0.06
    å»
    -0.06
    tery
    -0.06
    оÑĤо
    -0.06
    _rep
    -0.06
    以身
    -0.06
    POSITIVE LOGITS
    èµ·å§ĭ
    0.09
    -capital
    0.09
    å¼Ģ头çļĦ
    0.08
    çļĦé¦ĸ
    0.08
    å¼Ģ头
    0.08
    -start
    0.08
     starts
    0.08
    èµ·
    0.08
    èµ·æīĭ
    0.08
    awali
    0.08
    Activations Density 0.009%

    No Known Activations