© 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. 21166
    Prev
    Next
    INDEX
    Explanations

    constructor or method

    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
    ç½
    -0.05
    æĩIJ
    -0.05
    é¾ĻéŨ
    -0.05
    pci
    -0.05
    çĥŁ
    -0.05
    ÙĦÙĬ
    -0.05
     reporting
    -0.05
     sin
    -0.05
    åįĥéĩij
    -0.05
    лай
    -0.05
    POSITIVE LOGITS
    ç¹ķ
    0.06
     Pau
    0.06
     ÑĢобоÑĤÑĥ
    0.06
    åľ¨çº¿å®¢æľį
    0.06
     dw
    0.06
     ÅĽwiad
    0.06
    缺ä¸Ģ
    0.06
    andainya
    0.06
     excepc
    0.06
    eer
    0.06
    Activations Density 0.019%

    No Known Activations