© 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. 18192
    Prev
    Next
    INDEX
    Explanations

    vermis, Vitamins, Timeout

    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
    scher
    -0.09
    olda
    -0.09
    andon
    -0.08
    achim
    -0.08
    веде
    -0.08
    åIJ«éĩij
    -0.08
    ecker
    -0.08
    ÙĪسة
    -0.08
    èı²çī¹
    -0.08
    reden
    -0.08
    POSITIVE LOGITS
    åIJİè¦ģ
    0.07
    åIJİä¼ļ
    0.06
     lo
    0.06
     counter
    0.06
    DAQ
    0.06
    _sg
    0.06
    éĥ½å¾Ĺ
    0.05
    æŶä¼ļ
    0.05
     Manus
    0.05
     Lord
    0.05
    Activations Density 0.007%

    No Known Activations