© 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. 20994
    Prev
    Next
    INDEX
    Explanations

    physical examination revealed

    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
    elus
    -0.06
     ausz
    -0.06
     inz
    -0.05
    äºī
    -0.05
     verge
    -0.05
    findFirst
    -0.05
    essen
    -0.05
    etro
    -0.05
    æ·±çļĦ
    -0.05
    indo
    -0.05
    POSITIVE LOGITS
    åĴĮæĶ¿åºľ
    0.06
    åħ¥å¾®
    0.06
    body
    0.06
     body
    0.06
    iony
    0.05
    åĴĮåľ°æĸ¹
    0.05
    agn
    0.05
     Microsystems
    0.05
    ponent
    0.05
    åĴĮèīºæľ¯
    0.05
    Activations Density 0.023%

    No Known Activations