© 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. 40558
    Prev
    Next
    INDEX
    Explanations

    but, however, basically

    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
    oku
    -0.07
    irma
    -0.07
    oot
    -0.07
    åħ¶å®ŀ
    -0.07
    rvine
    -0.07
    Fall
    -0.07
    ä½ĨçĶ±äºİ
    -0.07
    apte
    -0.06
     fall
    -0.06
    wr
    -0.06
    POSITIVE LOGITS
     nonetheless
    0.15
     nevertheless
    0.14
     dennoch
    0.09
    æĢ»æ¯Ķ
    0.08
    ãģĿãĤĮãģ§ãĤĤ
    0.08
    ä¸Ģæĸij
    0.07
     rubbing
    0.07
    æĢ»ç®Ĺ
    0.07
    holz
    0.07
     Anyway
    0.07
    Activations Density 0.250%

    No Known Activations