© 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. 50748
    Prev
    Next
    INDEX
    Explanations

    dates with separators

    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
    ä¸įåĮħåIJ«
    -0.06
    çĺ¦èº«
    -0.06
    rim
    -0.06
    ÑģÑĢе
    -0.06
    (Controller
    -0.06
    驹
    -0.06
    jÃŃ
    -0.06
    å²
    -0.06
    佬
    -0.06
    缺ä¸Ģ
    -0.06
    POSITIVE LOGITS
    ElapsedTime
    0.08
    elp
    0.07
    ikit
    0.07
    æŁ¥çľĭåħ¨éĥ¨
    0.07
    æľºåħ³
    0.07
    ikers
    0.07
    aoke
    0.07
    ä¸Ńè§Ħ
    0.07
    åįĹé£İ
    0.07
    ศา
    0.07
    Activations Density 0.017%

    No Known Activations