© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22242
    Prev
    Next
    INDEX
    Explanations

    other or else

    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
     bay
    -0.05
    icker
    -0.05
    inki
    -0.05
    èIJ¥ä¸ļ
    -0.05
    æĪª
    -0.05
    аÑĤÑĥÑĢа
    -0.05
     Bay
    -0.05
    arus
    -0.05
     ide
    -0.05
     type
    -0.05
    POSITIVE LOGITS
     únicos
    0.06
     ways
    0.06
    æĥŁä¸Ģ
    0.06
    à¹Ģà¸Ķียว
    0.06
    одно
    0.06
    kesan
    0.06
    ways
    0.06
    人æĿIJ
    0.06
    theit
    0.06
     Way
    0.06
    Activations Density 0.008%

    No Known Activations