© 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. 17609
    Prev
    Next
    INDEX
    Explanations

    page references and technical terms

    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
    åĪĢåĪĥ
    -0.06
     vers
    -0.05
     Anci
    -0.05
    --,
    -0.05
    æľīæĿ¡ä¸įç´Ĭ
    -0.05
    rary
    -0.05
    zÄĻ
    -0.05
    kker
    -0.05
    /*/
    -0.05
    gett
    -0.05
    POSITIVE LOGITS
    amica
    0.06
    å¥Ĺ
    0.06
    ouse
    0.06
    лик
    0.06
    审
    0.06
    TOR
    0.06
    do
    0.06
    odo
    0.05
    ä¸Ģèµ·çİ©
    0.05
    onii
    0.05
    Activations Density 0.174%

    No Known Activations