© 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. 64500
    Prev
    Next
    INDEX
    Explanations

    currency or numbers

    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
     Mala
    -0.07
    å¯¹æľ¬æ¬¡
    -0.06
    lesh
    -0.06
    éĢļè¿ĩæľ¬æ¬¡
    -0.05
    IFE
    -0.05
     Bun
    -0.05
    ä¸įäºĮ
    -0.05
    uzu
    -0.05
    çļĦå°ıç¼ĸ
    -0.05
     McL
    -0.05
    POSITIVE LOGITS
    ordat
    0.08
    __$
    0.08
    olim
    0.08
    claimer
    0.08
    apikey
    0.08
    oplay
    0.07
    หาย
    0.07
    ctors
    0.07
    èģĮåijĺ
    0.07
    ALSE
    0.07
    Activations Density 0.039%

    No Known Activations