© 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. 35033
    Prev
    Next
    INDEX
    Explanations

    Team Lea

    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
    ä¸įæĶ¾
    -0.07
    urry
    -0.06
    iva
    -0.06
    -IS
    -0.06
    è£ħ车
    -0.06
    欧
    -0.06
    ÑĢке
    -0.06
    amet
    -0.05
    acle
    -0.05
    κολ
    -0.05
    POSITIVE LOGITS
    çĻ¾åĪĨä¹ĭçĻ¾
    0.08
     Catégorie
    0.07
    omatic
    0.07
    ä¸ŃåĽ½ç½ij
    0.07
     Cout
    0.07
     PhpStorm
    0.07
    elloworld
    0.07
    -gallery
    0.07
    alainen
    0.07
    oria
    0.07
    Activations Density 0.384%

    No Known Activations