© 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. 17635
    Prev
    Next
    INDEX
    Explanations

    code examples after `(`

    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
    ums
    -0.05
    驼
    -0.05
    ios
    -0.05
    éĤ£ä¸Ģ
    -0.05
     fle
    -0.05
     ag
    -0.05
     sut
    -0.05
    åį·
    -0.05
    itur
    -0.05
     R
    -0.05
    POSITIVE LOGITS
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.07
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.07
    å°ıç¼ĸå°±
    0.07
    acct
    0.06
    åIJĥå¾Ĺ
    0.06
    以ä¸ĭæĺ¯
    0.06
    åIJĨ
    0.06
    éļ¾æ±Ĥ
    0.06
    smarty
    0.06
     sobres
    0.06
    Activations Density 0.003%

    No Known Activations