© 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. 20481
    Prev
    Next
    INDEX
    Explanations

    acquisition and deal

    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
    arz
    -0.08
     opro
    -0.08
    æķħäºĭæĥħ
    -0.08
    pair
    -0.07
    _modify
    -0.07
    aida
    -0.07
    ä¹ŁæŃ£æĺ¯
    -0.07
    天æķ°
    -0.07
    åĽŀæĹĭ
    -0.07
    å¾ĹåIJį
    -0.07
    POSITIVE LOGITS
    å·²ç»ı
    0.11
     already
    0.11
    Ñĥже
    0.10
    å·²æĪIJ
    0.10
    å·²
    0.10
    å·²ç»ıä»İ
    0.09
     sudah
    0.09
    å·²ç»ıå°Ĩ
    0.09
    å·²ä»İ
    0.09
    æ¸Īãģ¿
    0.09
    Activations Density 0.007%

    No Known Activations