© 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. 17863
    Prev
    Next
    INDEX
    Explanations

    variable assignment statements

    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
    armi
    -0.06
    اÙħØ©
    -0.06
    ulton
    -0.06
    {}
    -0.06
    åIJ«
    -0.06
     moeite
    -0.05
    \\/
    -0.05
    æ½¼
    -0.05
    ampe
    -0.05
    ate
    -0.05
    POSITIVE LOGITS
    ett
    0.06
    æ°ijçĶ¨
    0.06
    ÛĮب
    0.06
     prak
    0.05
    es
    0.05
     subsequent
    0.05
    abilit
    0.05
    istou
    0.05
    çľ¼çIJĥ
    0.05
    etical
    0.05
    Activations Density 0.026%

    No Known Activations