© 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. 61170
    Prev
    Next
    INDEX
    Explanations

    assigning variables with let

    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
    å¾ĹæĿ¥
    -0.08
    imet
    -0.07
    æ¯ıä¸ĢæŃ¥
    -0.07
    endon
    -0.07
    åħ¶å¯¹
    -0.06
    éĽ¨éľ²
    -0.06
     jub
    -0.06
    éļ¾äºİ
    -0.06
    åı¯åı£
    -0.06
    å¾ĹçĽĬ
    -0.06
    POSITIVE LOGITS
    代表çļĦ
    0.09
    quil
    0.08
    æľīåı¯èĥ½æĺ¯
    0.08
     hypothetical
    0.07
    åı¯èĥ½æĺ¯
    0.07
    å¾Īåı¯èĥ½æĺ¯
    0.07
    eous
    0.07
     caut
    0.07
     Likely
    0.07
     likely
    0.07
    Activations Density 0.002%

    No Known Activations