© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20429
    Prev
    Next
    INDEX
    Explanations

    fractional measurements

    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
    èī¯ãģĦãģ§ãģĹãĤĩãģĨ
    -0.06
    ÙĪÛĮت
    -0.05
    ialized
    -0.05
    rowave
    -0.05
    cela
    -0.05
    folk
    -0.05
    åŃIJçļĦ
    -0.05
    _visibility
    -0.05
    pter
    -0.05
    å¿Ĺæĺİ
    -0.05
    POSITIVE LOGITS
    egn
    0.05
    ολ
    0.05
     (!!
    0.05
    วย
    0.05
    es
    0.05
    isex
    0.05
     dict
    0.05
     Nope
    0.05
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.05
    оÑģÑĤи
    0.05
    Activations Density 0.002%

    No Known Activations