© 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. 582
    Prev
    Next
    INDEX
    Explanations

    says that

    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
    æĸ¹å¼ı使çĶ¨
    -0.10
    кÑĤо
    -0.08
    å¥ij
    -0.07
     },{
    -0.07
    _LAT
    -0.07
     Ejem
    -0.07
    adari
    -0.07
    (serv
    -0.07
    ahan
    -0.07
    第ä¸Ģ家
    -0.07
    POSITIVE LOGITS
    em
    0.07
    ä¸ĩçī©
    0.07
    ap
    0.07
    å¥½ä¸ľè¥¿
    0.07
    alin
    0.06
    :
    0.06
    eks
    0.06
     justamente
    0.06
    =
    0.06
     bahwa
    0.06
    Activations Density 0.023%

    No Known Activations