© 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. 22135
    Prev
    Next
    INDEX
    Explanations

    Pauli matrices, vectors, data

    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
     Speedway
    -0.07
    ening
    -0.07
    atação
    -0.06
    æĮł
    -0.06
    stal
    -0.06
    renal
    -0.06
    ãĥĻãĥ¼ãĥĪ
    -0.06
    abet
    -0.06
    atio
    -0.06
    orate
    -0.06
    POSITIVE LOGITS
    usy
    0.08
    æĹĭ转
    0.08
    磩éĺµ
    0.08
    åħĭéĩĮ
    0.08
     matrix
    0.07
     Dres
    0.07
    matrix
    0.07
    nock
    0.07
    isky
    0.07
    uille
    0.07
    Activations Density 0.002%

    No Known Activations