© 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. 17494
    Prev
    Next
    INDEX
    Explanations

    then followed by "Object" or "For"

    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
    attie
    -0.06
     narrative
    -0.06
    orno
    -0.05
    天çİĭ
    -0.05
    æ¯ķç«Łæĺ¯
    -0.05
    èĻ½æĺ¯
    -0.05
    çļĦéĩįè¦ģæĢ§åĴĮ
    -0.05
    isht
    -0.05
    Ïīμα
    -0.05
    èĻ½çĦ¶æĺ¯
    -0.05
    POSITIVE LOGITS
    Ñħа
    0.06
    éĤ£å°±æĺ¯
    0.06
    举
    0.05
    eded
    0.05
    çĴŀ
    0.05
    ÙIJد
    0.05
    .follow
    0.05
    brug
    0.05
    anonymous
    0.05
    驱
    0.05
    Activations Density 0.060%

    No Known Activations