© 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. 41364
    Prev
    Next
    INDEX
    Explanations

    matrix notation

    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
    åĩ¡
    -0.09
    综åIJĪåĪĨæŀIJ
    -0.07
    æĦĪ
    -0.07
    itra
    -0.06
    noi
    -0.06
    åĸĬ
    -0.06
    ç¾¹
    -0.06
    glob
    -0.06
    ä¸įä¼ij
    -0.06
    åĩ¡æĺ¯
    -0.06
    POSITIVE LOGITS
    磩éĺµ
    0.08
    matrix
    0.08
     matrix
    0.08
    éºĵ
    0.08
    éĺµ
    0.08
     Semana
    0.08
    pmat
    0.08
     listing
    0.08
    erot
    0.08
    æľĿéĺ³
    0.08
    Activations Density 0.029%

    No Known Activations