© 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. 8608
    Prev
    Next
    INDEX
    Explanations

    physical descriptions or measurements

    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
    cek
    -0.07
    alos
    -0.07
    å¦ĤåĽł
    -0.07
    åıĪå¦Ĥä½ķ
    -0.07
    reto
    -0.07
    å¦ĤåĪĿ
    -0.07
    å³Ļ
    -0.07
    æľĢéĩįè¦ģçļĦæĺ¯
    -0.07
     Umfang
    -0.07
     Rang
    -0.07
    POSITIVE LOGITS
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.09
    ä¹Łå°±æĺ¯
    0.07
     plus
    0.07
     minus
    0.07
    åį³
    0.07
     itself
    0.07
    æ¦Ĥ论
    0.07
    没éĶĻ
    0.07
     Tiss
    0.06
    ynet
    0.06
    Activations Density 0.023%

    No Known Activations