© 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. 18740
    Prev
    Next
    INDEX
    Explanations

    function parameter lists

    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
    ogi
    -0.06
    esen
    -0.06
    thane
    -0.05
    åı°ä¸ĭ
    -0.05
    ű
    -0.05
    æĬĺ
    -0.05
     rota
    -0.05
    ständige
    -0.05
    à¹Ģà¸Ĺียà¸ļ
    -0.05
    alnız
    -0.05
    POSITIVE LOGITS
    nikami
    0.06
    énom
    0.06
    urs
    0.06
    lsi
    0.05
    ÙİÙijÙĦ
    0.05
    éģ
    0.05
    izmu
    0.05
    nC
    0.05
    повÑĸ
    0.05
    ARP
    0.05
    Activations Density 0.020%

    No Known Activations