© 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. 7075
    Prev
    Next
    INDEX
    Explanations

    mathematical theory structures

    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
    ç±³é«ĺ
    -0.07
     Ultim
    -0.07
    段çļĦ
    -0.07
    ÑĩаÑĤки
    -0.07
    wers
    -0.07
    åģļçĤº
    -0.07
     Nors
    -0.07
    åIJµéĹ¹
    -0.07
    SCALE
    -0.07
    عاÙĨ
    -0.07
    POSITIVE LOGITS
     induced
    0.09
     finest
    0.07
    -induced
    0.07
    araf
    0.07
     associated
    0.07
    åħ³èģĶ
    0.07
    -associated
    0.07
    -compatible
    0.07
    åħ·
    0.06
    associated
    0.06
    Activations Density 0.022%

    No Known Activations