© 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. 39523
    Prev
    Next
    INDEX
    Explanations

    publication titles or acronyms

    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
    arre
    -0.07
    ailer
    -0.07
     Falle
    -0.07
    ãĥ¼ãĥĦ
    -0.07
    feof
    -0.06
    grab
    -0.06
    ä¸īåħ¬
    -0.06
     Nordest
    -0.06
    ãģĹãģ¾ãģĹãģ¦
    -0.06
     XXL
    -0.06
    POSITIVE LOGITS
    碧海
    0.07
     rejo
    0.07
    bil
    0.07
    ptes
    0.07
    ocha
    0.06
    æľĭ
    0.06
     ness
    0.06
    heed
    0.06
     nato
    0.06
     in
    0.06
    Activations Density 0.172%

    No Known Activations