© 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. 22166
    Prev
    Next
    INDEX
    Explanations

    projection and estimation

    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
     Peker
    -0.07
    梳
    -0.07
    Coord
    -0.07
    ÑħÑĢо
    -0.07
    æ¿ĢåħīåĻ¨
    -0.07
    éĻIJ
    -0.07
    aghetti
    -0.07
    loid
    -0.07
    èģĶèµĽä¸Ń
    -0.06
    Ĥ¹
    -0.06
    POSITIVE LOGITS
     averages
    0.08
    AMA
    0.08
     averaging
    0.08
    éĩĩ
    0.08
    -circle
    0.07
    滤
    0.07
     filters
    0.07
    circle
    0.07
     circle
    0.07
     dilation
    0.07
    Activations Density 0.007%

    No Known Activations