© 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. 50390
    Prev
    Next
    INDEX
    Explanations

    special characters and 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
    μμ
    -0.08
    /--
    -0.07
    lacement
    -0.07
    太å®Ī
    -0.07
    insula
    -0.06
    .ci
    -0.06
    äºĨä¸Ģè·³
    -0.06
    ียร
    -0.06
    à§Ģর
    -0.06
    ண
    -0.06
    POSITIVE LOGITS
    Ñĥжи
    0.07
     sovere
    0.06
    ¥
    0.06
    iaÅĤa
    0.06
    isz
    0.06
    äºijé¾Ļ
    0.06
    amd
    0.06
    itionally
    0.06
    идÑĥ
    0.06
    лика
    0.06
    Activations Density 0.102%

    No Known Activations