© 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. 18763
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with operators

    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
    orium
    -0.06
    pera
    -0.06
    夫æĸ¯åŁº
    -0.06
    itary
    -0.06
    inox
    -0.06
    çļĦæŶåĢĻäºĨ
    -0.06
    è¶Ĭåıij
    -0.06
    ìĽ¨ìĸ´
    -0.06
    ed
    -0.05
    ency
    -0.05
    POSITIVE LOGITS
    еÑģÑĤи
    0.05
    åĩºåĵģ
    0.05
    æĸĩ件æĪĸ
    0.05
    çIJ¦
    0.05
    akers
    0.05
    åIJı
    0.05
    èĢĮæĹł
    0.05
    cieli
    0.05
     fick
    0.05
    èĢĮåĬ¨
    0.05
    Activations Density 0.032%

    No Known Activations