© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20430
    Prev
    Next
    INDEX
    Explanations

    cheaper method donation

    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
     xúc
    -0.06
     primit
    -0.06
    æİĴ
    -0.06
    odel
    -0.06
    並ãģ³
    -0.05
    æİĴçļĦ
    -0.05
    天ä¸Ģ
    -0.05
    åĦĢ
    -0.05
    åħī大
    -0.05
    æķ¬ç¤¼
    -0.05
    POSITIVE LOGITS
    ä¸Ĭæĸ°
    0.06
    aby
    0.06
    çļĦé«ĺè´¨éĩı
    0.06
    ervi
    0.06
    æ¯Ķ以å¾Ģ
    0.06
     vets
    0.05
     réuss
    0.05
     rejuven
    0.05
     Patch
    0.05
     destabil
    0.05
    Activations Density 0.006%

    No Known Activations