© 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. 15339
    Prev
    Next
    INDEX
    Explanations

    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
    æ±İ
    -0.08
    æļ¦
    -0.08
    uté
    -0.08
    ()._
    -0.07
    cop
    -0.07
    elok
    -0.07
    æŁ¯
    -0.07
     breathe
    -0.07
     generali
    -0.07
    ’y
    -0.07
    POSITIVE LOGITS
    æīįç®Ĺ
    0.09
     strict
    0.09
     ONLY
    0.08
     only
    0.08
    strict
    0.08
     Only
    0.08
    à¹Ģà¸Ĺà¹Īาà¸Ļัà¹īà¸Ļ
    0.08
     strictly
    0.08
    Only
    0.07
     absent
    0.07
    Activations Density 0.025%

    No Known Activations