© 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. 56296
    Prev
    Next
    INDEX
    Explanations

    population was

    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
    æѦè£ħ
    -0.08
    éļIJ
    -0.08
    主ä¹ī
    -0.08
    zel
    -0.07
     Ways
    -0.07
    åĽłä¸ºè¿Ļ
    -0.06
    室
    -0.06
    åĽłä¸º
    -0.06
     вÑĢоде
    -0.06
    åĽłä¸ºåľ¨
    -0.06
    POSITIVE LOGITS
    اتÙĬ
    0.08
     kele
    0.07
    (es
    0.07
    álu
    0.07
    为æĤ¨æݨèįIJ
    0.07
    omar
    0.07
     **.**
    0.07
     #__
    0.07
    ominio
    0.07
    оби
    0.07
    Activations Density 0.009%

    No Known Activations