© 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. 50326
    Prev
    Next
    INDEX
    Explanations

    comment termination

    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
    orn
    -0.08
    PropTypes
    -0.07
    ock
    -0.07
    idor
    -0.07
     Heard
    -0.07
    ider
    -0.07
    ãĤ¼
    -0.07
    æ¢
    -0.06
    .TestCheck
    -0.06
    sez
    -0.06
    POSITIVE LOGITS
    erias
    0.07
    æŃ£æĸĩ
    0.07
    vore
    0.07
    baugh
    0.07
    nip
    0.06
    bod
    0.06
    æĭĩ
    0.06
    ↵↵↵↵↵
    0.06
    BEGIN
    0.06
     ↵↵↵
    0.06
    Activations Density 0.289%

    No Known Activations