© 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. 20225
    Prev
    Next
    INDEX
    Explanations

    English translation equivalents

    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
    à¸ģู
    -0.07
    åŃ¦ä»¥èĩ´
    -0.07
    lore
    -0.07
     Interesting
    -0.07
     оÑĤÑģе
    -0.07
    ä¸įæĩĤå¾Ĺ
    -0.07
    umul
    -0.07
    inster
    -0.06
    WOR
    -0.06
    ouse
    -0.06
    POSITIVE LOGITS
     equivalents
    0.12
     equivalent
    0.11
     equivalente
    0.09
     Equivalent
    0.08
    æıIJ
    0.08
    Equivalent
    0.08
    æ±īè¯Ń
    0.07
    .Emit
    0.07
    çĽ¸å¯¹åºĶ
    0.07
    æĥħ
    0.07
    Activations Density 0.054%

    No Known Activations