© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22462
    Prev
    Next
    INDEX
    Explanations

    service, app, AI, business

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Schnell
    -0.07
    é§Ĵ
    -0.07
    atters
    -0.07
    aggio
    -0.06
     Accord
    -0.06
    udes
    -0.06
    çĶµèĦijçīĪ
    -0.06
    /front
    -0.06
    ascal
    -0.06
    angers
    -0.06
    POSITIVE LOGITS
     whether
    0.05
    æ¯ıä½į
    0.05
     n
    0.05
    ä½įç½®
    0.05
     candidates
    0.05
    ourt
    0.05
     f
    0.05
     visible
    0.04
     Antar
    0.04
    åºĶ该就æĺ¯
    0.04
    Activations Density 0.002%

    No Known Activations