© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19477
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, or alphanumeric identifiers

    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
    çļĦçĭĢæ³ģ
    -0.06
    leta
    -0.06
    ä¸ĭåIJĮ
    -0.06
    arco
    -0.06
     Gouver
    -0.06
    uken
    -0.06
    -rich
    -0.05
    Dienst
    -0.05
    öv
    -0.05
    çļĦåį±éĻ©
    -0.05
    POSITIVE LOGITS
    ris
    0.06
    ocker
    0.06
    à¹Ĩ
    0.06
     Aless
    0.05
    åģı
    0.05
    åĴĮä¸ī
    0.05
    enix
    0.05
    oha
    0.05
    åĦ¿
    0.05
    天åħĥ
    0.05
    Activations Density 0.117%

    No Known Activations