© 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. 17519
    Prev
    Next
    INDEX
    Explanations

    series titles and descriptions

    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
    çļĦä¸Ģçŀ¬éĹ´
    -0.06
    å¼¥
    -0.06
    odie
    -0.05
    pel
    -0.05
    bol
    -0.05
    ä¸įæĪIJåĬŁ
    -0.05
    ä½ĵ积å°ı
    -0.05
    اØŃ
    -0.05
    æĦ§
    -0.05
     occasion
    -0.05
    POSITIVE LOGITS
    å§ĭ
    0.06
     Anfang
    0.06
    onomia
    0.06
     benefici
    0.06
    hamdul
    0.06
     Tire
    0.06
    æĶ¶çĽĬ
    0.06
    æİ¥æĽ¿
    0.06
    å·²å®Įç»ĵ
    0.05
    á»Ļn
    0.05
    Activations Density 0.036%

    No Known Activations