© 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. 21806
    Prev
    Next
    INDEX
    Explanations

    should also

    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
    鹿
    -0.06
    广
    -0.06
    åĴĮå¹³
    -0.06
    æŃ£ä¹ī
    -0.05
    Transform
    -0.05
    ulant
    -0.05
    åĪ©
    -0.05
     аг
    -0.05
    Ca
    -0.05
    æ¾Ħ
    -0.05
    POSITIVE LOGITS
    also
    0.06
     Juga
    0.06
     also
    0.06
     sebe
    0.05
    æľĢç®ĢåįķçļĦ
    0.05
    è¿Ļæł¹
    0.05
    åħ»æĪIJèī¯å¥½çļĦ
    0.05
     Nice
    0.05
    ÑĢев
    0.05
    åħīåįİ
    0.05
    Activations Density 0.210%

    No Known Activations