© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17016
    Prev
    Next
    INDEX
    Explanations

    access to

    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
    Not in Any Lists

    No Comments

    Negative Logits
    less
    -0.06
    ally
    -0.05
    v
    -0.05
    ew
    -0.05
    he
    -0.05
    istic
    -0.05
    ierung
    -0.05
    sh
    -0.05
    ged
    -0.05
     prospects
    -0.05
    POSITIVE LOGITS
    à¸Ļà¹Į
    0.07
    atoare
    0.07
    bsd
    0.07
    ampion
    0.07
    åIJĮæľŁ
    0.07
    DIC
    0.07
    åĴĮ解
    0.06
    ÙĨدÙĩ
    0.06
    æĽ´å¹¿
    0.06
    .unbind
    0.06
    Activations Density 0.018%

    No Known Activations