© 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. 9430
    Prev
    Next
    INDEX
    Explanations

    character encoding

    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
    çIJĽ
    -0.08
    ä¸Ĭ空
    -0.07
    imps
    -0.07
    ievi
    -0.07
     Rope
    -0.07
    åĽ
    -0.07
    èĦ±èIJ½
    -0.07
    uess
    -0.07
    veral
    -0.07
    æģ¶
    -0.06
    POSITIVE LOGITS
     Hmm
    0.07
    PACE
    0.07
    ÑĢено
    0.07
    ãĤĵãģĺãĤĥ
    0.07
    -factor
    0.06
    并ä¸į容æĺĵ
    0.06
    idrat
    0.06
    ä¸įæĺ¯å¾Ī好
    0.06
    PLY
    0.06
    ä¸įæĺ¯å¾Ī
    0.06
    Activations Density 0.005%

    No Known Activations