© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10625
    Prev
    Next
    INDEX
    Explanations

    groups, points, lines, weeks, stages

    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
    their
    -0.07
     leur
    -0.07
    sv
    -0.07
     Their
    -0.06
    sWith
    -0.06
    ton
    -0.06
    antik
    -0.06
     their
    -0.06
    sm
    -0.06
    rit
    -0.06
    POSITIVE LOGITS
    ä¸ĢåĪ°
    0.10
    ä¸Ģèĩ³
    0.10
    hots
    0.09
    ×Ļר×ķ
    0.08
    оÑģÑģ
    0.08
    åij¨ä¸Ģèĩ³
    0.08
    ugier
    0.08
    imple
    0.08
    åIJĪ
    0.08
    ابÙĬÙĨ
    0.08
    Activations Density 0.083%

    No Known Activations