© 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. 21958
    Prev
    Next
    INDEX
    Explanations

    health, engineering, and science fields

    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
    大åı¯
    -0.07
    æĸ°ç¤¾
    -0.07
    æľīåħ³äºİ
    -0.06
    éĶ¦æ¶Ľ
    -0.06
    .standard
    -0.06
    antin
    -0.06
    ürf
    -0.06
    è¿Ļæĸ¹éĿ¢çļĦ
    -0.06
    åĬŁäºİ
    -0.06
    -season
    -0.06
    POSITIVE LOGITS
    临
    0.07
    åĽ´
    0.06
    ä¸Ķ
    0.05
     dun
    0.05
    èĩ¨
    0.05
     май
    0.05
    aku
    0.05
    åīįåį«
    0.05
    geb
    0.05
    缮
    0.05
    Activations Density 0.022%

    No Known Activations