© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20167
    Prev
    Next
    INDEX
    Explanations

    database 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
    人æĪĸ
    -0.07
    æ´»åĬ¨åĴĮ
    -0.06
     سع
    -0.06
     irres
    -0.06
    好书
    -0.06
    ç»ı审çIJĨ
    -0.06
    çī©åĴĮ
    -0.06
    atitis
    -0.06
    è§Ĥ念åĴĮ
    -0.06
    iteli
    -0.06
    POSITIVE LOGITS
    ring
    0.05
    çIJĨ
    0.05
    nu
    0.04
    .cgi
    0.04
    hal
    0.04
    uly
    0.04
    çļ®æ¯Ľ
    0.04
    éĩįä»»
    0.04
     Mark
    0.04
    }*
    0.04
    Activations Density 0.020%

    No Known Activations