© 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. 27601
    Prev
    Next
    INDEX
    Explanations

    in followed by this or the

    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
    æľĪåľ¨
    -0.07
    hein
    -0.07
    tide
    -0.07
    orce
    -0.06
    ritte
    -0.06
    ighth
    -0.06
     inn
    -0.06
    å¹¼åĦ¿åľ¨
    -0.06
    оеди
    -0.06
    åľ¨æ¸¸æĪı
    -0.06
    POSITIVE LOGITS
     hindsight
    0.10
     entanto
    0.09
    arg
    0.09
     absence
    0.08
    æŃ£å¸¸æĥħåĨµä¸ĭ
    0.08
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    0.08
    gle
    0.08
    大å¤ļæķ°
    0.08
    opal
    0.08
    çİ°å®ŀçĶŁæ´»ä¸Ń
    0.08
    Activations Density 0.262%

    No Known Activations