© 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. 13845
    Prev
    Next
    INDEX
    Explanations

    traceback

    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
    imet
    -0.07
    æĤ¨çļĦè¯Ħ论
    -0.07
    UnderTest
    -0.07
    linger
    -0.07
    umerator
    -0.07
    æĸĩåĵ²
    -0.07
    enn
    -0.07
    agi
    -0.07
    bye
    -0.07
    entifier
    -0.07
    POSITIVE LOGITS
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    0.08
    ×ķ
    0.07
    à¸ģารà¸Ĺำà¸ĩาà¸Ļà¸Ĥà¸Ńà¸ĩ
    0.07
     (*((
    0.07
    èĪ¬åľ°
    0.07
    éĢļãĤĬ
    0.07
    arya
    0.07
    jectory
    0.07
    annot
    0.07
     Ñħод
    0.07
    Activations Density 0.002%

    No Known Activations