© 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. 19865
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols

    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
     whoever
    -0.06
    åİŁåĽłåľ¨äºİ
    -0.06
     whatever
    -0.06
    æİ
    -0.05
    äl
    -0.05
    åİŁåĽłå°±æĺ¯
    -0.05
    omie
    -0.05
    Õ¡Õµ
    -0.05
    æĸ°åĬłåĿ¡
    -0.05
    веÑĢи
    -0.05
    POSITIVE LOGITS
    ØŁ
    0.07
    è¿Ļä¹Īå¿«
    0.07
    ï¼Ł”
    0.07
    ?"
    0.07
    )?
    0.07
    }?
    0.07
    ï¼Ł
    0.07
    åIJĮæŶåıĪ
    0.07
    åıĪå¦Ĥä½ķ
    0.06
    åı¯ä»¥åIJĹ
    0.06
    Activations Density 0.016%

    No Known Activations