© 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. 27598
    Prev
    Next
    INDEX
    Explanations

    vector/velocity operations

    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
    è¿Ļ个æķ°åŃĹ
    -0.08
    alit
    -0.07
    ä¸ĭéĻIJ
    -0.07
     decimal
    -0.07
    ä¸ĬéĻIJ
    -0.07
    两ä½įæķ°
    -0.07
    å°ıæķ°
    -0.06
    estroy
    -0.06
     strip
    -0.06
    imity
    -0.06
    POSITIVE LOGITS
     vectors
    0.15
     vector
    0.15
    vector
    0.15
    Vector
    0.15
    çŁ¢éĩı
    0.14
    Vectors
    0.14
    åIJijéĩı
    0.14
    -vector
    0.14
     Vector
    0.13
    çŁ¢
    0.13
    Activations Density 0.009%

    No Known Activations