© 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. 21550
    Prev
    Next
    INDEX
    Explanations

    John, Defendants

    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
    å¤ĩ
    -0.06
    æ±°
    -0.06
    `\
    -0.06
     ë°ĸìĹIJ
    -0.06
    vole
    -0.06
    ambilan
    -0.06
    奴
    -0.06
    管çIJĨå§Ķåijĺä¼ļ
    -0.05
    ivid
    -0.05
    تÙĩÙĬ
    -0.05
    POSITIVE LOGITS
    елей
    0.06
    ìĹ°
    0.06
     géné
    0.06
    udara
    0.05
    ect
    0.05
    egers
    0.05
    orate
    0.05
    åĦ¡
    0.05
    ä¸Ģå±Ĭ
    0.05
    ebed
    0.05
    Activations Density 0.016%

    No Known Activations