© 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. 38020
    Prev
    Next
    INDEX
    Explanations

    wave vector and momentum

    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
    ektiv
    -0.07
    ipur
    -0.07
    ipan
    -0.07
    -toggler
    -0.06
    çĤ¹æ»´
    -0.06
    æĢ§åŃIJ
    -0.06
    åį±éļ¾
    -0.06
    èµĶ
    -0.06
    å¤©æ±ł
    -0.06
     collapsing
    -0.06
    POSITIVE LOGITS
    çŁ¢
    0.08
     волнÑĭ
    0.08
     waves
    0.08
    åĽŀç¨ĭ
    0.08
    å¹ħ
    0.08
    æĸ¹ä½į
    0.08
    çŁ¢éĩı
    0.08
     vạch
    0.08
    笼
    0.07
    essel
    0.07
    Activations Density 0.004%

    No Known Activations