© 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. 3768
    Prev
    Next
    INDEX
    Explanations

    GNU MP Library

    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
    æĢ§åľ°
    -0.07
    (crate
    -0.07
    æį®æѤ
    -0.06
     lainnya
    -0.06
     gì
    -0.06
    ä¹Łéļıä¹ĭ
    -0.06
    ilit
    -0.06
    åį´åľ¨
    -0.06
    åħ¶ä¸ī
    -0.06
    ä¹ŁåĽłæѤ
    -0.06
    POSITIVE LOGITS
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    0.08
    baugh
    0.08
     firstly
    0.08
    erede
    0.08
    éĢļ常æĥħåĨµä¸ĭ
    0.08
    ä¸ĢèĪ¬çļĦ
    0.08
    ãĤĤãģĹ
    0.08
     erster
    0.08
     suppose
    0.08
    mener
    0.08
    Activations Density 0.003%

    No Known Activations