© 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. 8854
    Prev
    Next
    INDEX
    Explanations

    years indicating specific events

    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
    ëłĮ
    -0.08
    تÙĩا
    -0.07
    è²Ķè²ħ
    -0.07
    ulaire
    -0.07
    ilé
    -0.07
    à¸Ħà¹īาà¸ĩ
    -0.07
    bind
    -0.07
    onyme
    -0.07
    ulare
    -0.07
    ä¸įå¾Ĺ
    -0.07
    POSITIVE LOGITS
    çŃł
    0.08
    æľ«
    0.07
     nostalg
    0.07
    yen
    0.07
    gba
    0.07
    gol
    0.06
    el
    0.06
    cess
    0.06
    gone
    0.06
    æĢĢæŧ
    0.06
    Activations Density 0.238%

    No Known Activations