© 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. 28167
    Prev
    Next
    INDEX
    Explanations

    most important thing

    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
    ehr
    -0.10
    ecz
    -0.08
    ContextMenu
    -0.08
    ÑģнÑĥ
    -0.08
    ggi
    -0.08
    hev
    -0.08
     legitimately
    -0.08
    çļĦ大好
    -0.08
    ANTS
    -0.08
    âĸ·
    -0.08
    POSITIVE LOGITS
    个人认为
    0.08
     among
    0.08
    åĴĮæľĢ
    0.07
    åľ¨ä¼Ĺå¤ļ
    0.07
     arguably
    0.07
    æľĢéĩįè¦ģçļĦ
    0.07
    åħ³å¤´
    0.07
    éĩįä¸Ńä¹ĭéĩį
    0.07
    lya
    0.07
    æĬĵ
    0.06
    Activations Density 0.033%

    No Known Activations