© 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. 20907
    Prev
    Next
    INDEX
    Explanations

    POST method definition

    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
    aph
    -0.07
    åħ¥å¾®
    -0.06
    atus
    -0.05
     favor
    -0.05
    ä¸Ģæł·çļĦ
    -0.05
    hav
    -0.05
    ¹
    -0.05
    orne
    -0.05
     Mild
    -0.05
    çļĦåIJĮæŶ
    -0.05
    POSITIVE LOGITS
     multic
    0.06
     programm
    0.06
    stackpath
    0.06
    对å®ĥ
    0.05
    /xhtml
    0.05
     ekstrem
    0.05
    uttur
    0.05
    Programm
    0.05
    èĪĪ
    0.05
    Levels
    0.05
    Activations Density 0.001%

    No Known Activations