© 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. 17064
    Prev
    Next
    INDEX
    Explanations

    -up / -down sequences

    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
    æŃ»
    -0.06
    åı¯ä»¥æł¹æį®èĩªå·±çļĦ
    -0.05
    Dead
    -0.05
    <-
    -0.05
    æŃ¢æįŁ
    -0.05
    sit
    -0.05
    alic
    -0.05
     ful
    -0.05
    æŀŃ
    -0.05
    ÑĪим
    -0.05
    POSITIVE LOGITS
    åĬ¨äºĨ
    0.06
    placer
    0.06
    éĢIJæŃ¥
    0.06
    anser
    0.05
    漫游
    0.05
    次è¦ģ
    0.05
    icana
    0.05
    untut
    0.05
    éħ¥
    0.05
    scope
    0.05
    Activations Density 0.001%

    No Known Activations