© 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. 18036
    Prev
    Next
    INDEX
    Explanations

    code blocks, options, and syntax

    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
     sam
    -0.05
    è¡ĢçļĦ
    -0.05
    ells
    -0.05
    elling
    -0.05
     c
    -0.05
    æĭ¨
    -0.05
    åĴ¬
    -0.05
    agra
    -0.05
    æ¶Į
    -0.05
    ä½ķæŶ
    -0.05
    POSITIVE LOGITS
    æľīçĪ±
    0.07
    æĺ¯è¯¥
    0.06
    obot
    0.06
    opy
    0.06
    è¯¥æľº
    0.06
    çĽ¸ä¼¼æĸĩçĮ®
    0.06
    átk
    0.06
     Cám
    0.06
    èĭ±æĸĩåŃĹ
    0.06
    opp
    0.06
    Activations Density 0.091%

    No Known Activations