© 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. 22521
    Prev
    Next
    INDEX
    Explanations

    study outcomes and strategies

    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
    ram
    -0.06
    edi
    -0.06
    SCREEN
    -0.06
    schirm
    -0.06
    screen
    -0.06
    Ùģس
    -0.05
    .Screen
    -0.05
    est
    -0.05
    ä¿¡çĶ¨
    -0.05
    óz
    -0.05
    POSITIVE LOGITS
    onse
    0.06
    chter
    0.06
     natte
    0.05
    *sp
    0.05
     ÑģпÑĢи
    0.05
    WebpackPlugin
    0.05
    ë°ĽìķĦ
    0.05
     entirety
    0.05
    ç¼ł
    0.05
     chung
    0.05
    Activations Density 0.015%

    No Known Activations