© 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. 22518
    Prev
    Next
    INDEX
    Explanations

    financial documents

    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
    øk
    -0.06
    inga
    -0.06
    iram
    -0.06
    å¥Īä½ķ
    -0.06
    aland
    -0.06
    iles
    -0.06
    vania
    -0.05
    å¸Ń
    -0.05
    erche
    -0.05
    øg
    -0.05
    POSITIVE LOGITS
    模ç³Ĭ
    0.06
    éĽħ
    0.06
     enough
    0.05
     gener
    0.05
    æ³Ľ
    0.05
    æĹı
    0.05
    tol
    0.05
    iny
    0.05
    åIJĪ秣
    0.05
    /general
    0.05
    Activations Density 0.001%

    No Known Activations