© 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. 14424
    Prev
    Next
    INDEX
    Explanations

    step followed by numbers or symbols

    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
    emy
    -0.09
    æľ¬ç«ĻåĨħ容
    -0.08
    ohana
    -0.08
     Machado
    -0.08
    Ñģмо
    -0.08
    èĴ¸èĴ¸
    -0.08
    订éĺħä¸ĵæłı
    -0.08
    utherland
    -0.08
    usra
    -0.07
    onato
    -0.07
    POSITIVE LOGITS
     first
    0.08
     First
    0.07
    hed
    0.07
    First
    0.07
    ĴĪ
    0.07
    1
    0.07
    çģ¿
    0.06
    ä¹ĭä¸Ģ
    0.06
     Firstly
    0.06
    é¦ĸåħĪåľ¨
    0.06
    Activations Density 0.002%

    No Known Activations