© 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. 51574
    Prev
    Next
    INDEX
    Explanations

    now to be written

    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
    elaar
    -0.09
     PREV
    -0.08
    æķĪ
    -0.08
    неж
    -0.07
    ép
    -0.07
    èĭ¹
    -0.07
    urah
    -0.07
    educt
    -0.07
    åĴĮå¹³
    -0.07
    åıĪ好
    -0.07
    POSITIVE LOGITS
    æĽ´å®¹æĺĵ
    0.09
     whereas
    0.08
    æĽ´æĸ¹ä¾¿
    0.07
    缸æ¯Ķä¹ĭä¸ĭ
    0.07
    igt
    0.07
    æĽ´èĥ½
    0.07
     hingegen
    0.07
    æīįèĥ½æĽ´å¥½åľ°
    0.07
    è½»æĿ¾åľ°
    0.07
    uhan
    0.07
    Activations Density 0.148%

    No Known Activations