© 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. 57577
    Prev
    Next
    INDEX
    Explanations

    PhD degrees and affiliations

    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
    çĪ¶å¥³
    -0.08
    æĺ§
    -0.08
    iglia
    -0.08
    _tab
    -0.08
    è¿Ļ次活åĬ¨
    -0.08
    ÙĪعات
    -0.07
     ÑĤаб
    -0.07
    outh
    -0.07
    大åIJĥ
    -0.07
    -tab
    -0.07
    POSITIVE LOGITS
    æ·±éĢł
    0.08
    çłĶ究çĶŁçļĦ
    0.07
    /master
    0.07
    æĶ»è¯»
    0.07
    éļİ
    0.07
    çłĶ究æĸ¹åIJij
    0.07
    çĶ¨ä¹¦
    0.06
     @_
    0.06
    åĬłæĮģ
    0.06
     PhD
    0.06
    Activations Density 0.090%

    No Known Activations