© 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. 16910
    Prev
    Next
    INDEX
    Explanations

    Swedish, Edmund Burke

    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
    æĸ°åĬłåĿ¡
    -0.07
    缸åħ³è´Łè´£äººè¡¨ç¤º
    -0.06
     behalf
    -0.05
     pierced
    -0.05
    eks
    -0.05
    okr
    -0.05
    æº
    -0.05
    ocus
    -0.05
     }(
    -0.05
    缩水
    -0.05
    POSITIVE LOGITS
     entf
    0.06
    ç¿ģ
    0.06
    Ðĵи
    0.06
    ãģĬåĭ§ãĤģ
    0.06
    ivil
    0.06
    çIJĨ解åĴĮ
    0.06
    naval
    0.05
    apot
    0.05
    çŃīåIJĮ
    0.05
     confé
    0.05
    Activations Density 0.001%

    No Known Activations