© 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. 22461
    Prev
    Next
    INDEX
    Explanations

    let me

    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
    ä¸įè¦ģ让
    -0.05
    yan
    -0.05
    ãģŀ
    -0.05
    æĪij们ä¸Ģèµ·
    -0.05
    ely
    -0.05
    нибÑĥдÑĮ
    -0.05
    wf
    -0.05
    æŶåĢĻ
    -0.05
    æ¡ĤåĨł
    -0.05
    иви
    -0.05
    POSITIVE LOGITS
    ï¸ı
    0.07
    éĢĤçĶ¨
    0.06
    trit
    0.06
    .dk
    0.06
    ers
    0.06
    à¸ķà¹Īาà¸ĩ
    0.06
    éĢĤçĶ¨çļĦ
    0.06
    çļĦéľĢæ±Ĥ
    0.06
    akat
    0.06
    оÑĢга
    0.06
    Activations Density 0.026%

    No Known Activations