© 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. 20329
    Prev
    Next
    INDEX
    Explanations

    known to

    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
    ynd
    -0.06
    ÑĭваÑİÑĤ
    -0.06
    isos
    -0.06
    oudre
    -0.06
     inconven
    -0.06
     complementar
    -0.06
    à¸Ĭม
    -0.06
    ä¸Ģ个人çļĦ
    -0.06
    yre
    -0.06
    sms
    -0.06
    POSITIVE LOGITS
     V
    0.06
    åª
    0.06
    нка
    0.06
     Level
    0.05
    ÙĨدÙĩ
    0.05
    åģı
    0.05
    æļ®
    0.05
    Level
    0.05
    ret
    0.05
     ÑĦона
    0.05
    Activations Density 0.005%

    No Known Activations