© 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. 63430
    Prev
    Next
    INDEX
    Explanations

    matrix dimensions

    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
    sstr
    -0.07
    arani
    -0.07
    _BUCKET
    -0.07
    ãĥĥãĤ±
    -0.07
    åį
    -0.07
    uml
    -0.07
     minut
    -0.06
    alow
    -0.06
    éĶ¦æłĩ
    -0.06
    å·®ä¸į
    -0.06
    POSITIVE LOGITS
    ç»Ħç»ĩæľºæŀĦ
    0.07
    横
    0.07
    ä¸Ĭ空
    0.07
    ายà¸Ļ
    0.07
    å¤ļå°ij人
    0.07
    Dims
    0.07
    orgot
    0.07
    åıĺæĽ´åīį
    0.07
     Dimension
    0.07
    .ndim
    0.07
    Activations Density 0.047%

    No Known Activations