© 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. 44610
    Prev
    Next
    INDEX
    Explanations

    $\exists$ x or $\forall$ y

    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
    ords
    -0.08
     Tham
    -0.07
    áŀĦ
    -0.07
    ÏĮÏĤ
    -0.07
    æĶ¶ç¼´
    -0.07
     reflections
    -0.07
    åĽº
    -0.06
    amenti
    -0.06
    leur
    -0.06
    BOARD
    -0.06
    POSITIVE LOGITS
    à¹īา
    0.09
     Sez
    0.08
    rema
    0.07
    ive
    0.07
    符åIJĪåĽ½å®¶
    0.07
    天亮
    0.07
     Populate
    0.07
    aye
    0.07
    oused
    0.07
    abox
    0.07
    Activations Density 0.005%

    No Known Activations