© 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. 38407
    Prev
    Next
    INDEX
    Explanations

    building structure component

    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
    ÑĢоки
    -0.07
    kke
    -0.07
    æĸ¹èĪŁ
    -0.07
    estin
    -0.07
    åĽĽåij¨
    -0.07
    buzz
    -0.07
    ugo
    -0.07
    ä¹ĭ以
    -0.07
    æĿ¥è¶Ĭ
    -0.07
    ¿
    -0.07
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.10
     rather
    0.10
    èĢĮéĿŀ
    0.09
    rather
    0.09
    éĥ½æľīåı¯èĥ½
    0.09
    éĤ£éĩĮ
    0.08
    æĪĸèĢħæĺ¯
    0.08
    éĤ£åĦ¿
    0.08
     piuttosto
    0.08
    à¹Ģลยà¸Ĺีà¹Ģà¸Ķียว
    0.08
    Activations Density 0.119%

    No Known Activations