© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26817
    Prev
    Next
    INDEX
    Explanations

    talent, talented, only

    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
    ess
    -0.08
    æĪij们å°Ĩä¼ļ
    -0.07
    odiac
    -0.07
    ãģ¦ãĤĤ
    -0.07
     Æ¡i
    -0.07
     godt
    -0.07
    é¹ĥ
    -0.07
    XHR
    -0.07
    ors
    -0.07
    elin
    -0.07
    POSITIVE LOGITS
    (ca
    0.09
    å¾Ĺä¸Ĭ
    0.08
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.08
    ulat
    0.08
    å¾Ĺèµ·
    0.08
     mẻ
    0.08
    fully
    0.08
    åĪļåĪļå¼Ģå§ĭ
    0.08
    DMETHOD
    0.08
    åIJįåī¯åħ¶å®ŀçļĦ
    0.08
    Activations Density 0.005%

    No Known Activations