© 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. 10186
    Prev
    Next
    INDEX
    Explanations

    starts of code comments

    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
    puis
    -0.08
     Sujet
    -0.07
    rawer
    -0.07
    bility
    -0.06
    çĥŃéŨæIJľç´¢
    -0.06
    æ»
    -0.06
    ught
    -0.06
    ât
    -0.06
    éĢĨè¡Į
    -0.06
    Å¡tÃŃ
    -0.06
    POSITIVE LOGITS
    对ä¸Ĭè¿°
    0.08
    warts
    0.07
    å¯¹åľ¨
    0.07
    容
    0.07
    åİļå¾·
    0.07
    åĽ½å®¶è§Ħå®ļ
    0.07
     Merdeka
    0.07
    ohan
    0.07
    ullan
    0.07
    iliz
    0.07
    Activations Density 0.014%

    No Known Activations