© 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. 22495
    Prev
    Next
    INDEX
    Explanations

    stamps pack

    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
    inges
    -0.06
    elow
    -0.06
    æ¯Ķæĸ¹
    -0.06
    çĤ¹çĿĽ
    -0.06
    جابة
    -0.06
     Syarat
    -0.06
    orse
    -0.05
     Alps
    -0.05
    ringe
    -0.05
    onald
    -0.05
    POSITIVE LOGITS
    åľ¨æ¸¸æĪıä¸Ń
    0.06
     cub
    0.05
    activated
    0.05
    WF
    0.05
     Flo
    0.05
    UFFER
    0.05
     activated
    0.05
    æŀ¢
    0.05
    éĻį
    0.05
    æ·ij女
    0.05
    Activations Density 0.286%

    No Known Activations