© 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. 12319
    Prev
    Next
    INDEX
    Explanations

    Mai, Castle, captured, games, ARP, Cave

    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
    ãģĵãģ¡ãĤīãĤĤ
    -0.11
    çŃīåħ¶ä»ĸ
    -0.11
     infine
    -0.09
    ãģĵãĤĮãĤĤ
    -0.09
    ä»Ĭ度ãģ¯
    -0.08
     Lastly
    -0.08
     ebenfalls
    -0.08
     enfin
    -0.08
    è·ĥè·ĥ欲è¯ķ
    -0.08
    again
    -0.08
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.09
    0.07
    ↵
    0.06
     B
    0.06
    åıĪå¦Ĥ
    0.05
    (
    0.05
    ,
    0.05
     [
    0.05
    [
    0.05
     (
    0.05
    Activations Density 5.735%

    No Known Activations