© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37506
    Prev
    Next
    INDEX
    Explanations

    label/field separators

    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
    Negative Logits
    ÙĤاÙħ
    -0.07
    ">@
    -0.07
     '&'
    -0.06
    å¢ĥåľ°
    -0.06
    dge
    -0.06
     ÙħÙĤاÙħ
    -0.06
    ndata
    -0.06
    ends
    -0.06
    åĸ·å°Ħ
    -0.06
    éĶ¢
    -0.06
    POSITIVE LOGITS
    ___
    0.08
    _________
    0.08
    ____________
    0.08
    _____
    0.08
     XXX
    0.08
     _____
    0.08
     __________________
    0.08
     ___
    0.08
    ________
    0.08
     ______
    0.08
    Activations Density 0.059%

    No Known Activations