© 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. 18801
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    idd
    -0.05
     the
    -0.05
     (
    -0.05
     its
    -0.05
    à¹Ĩ
    -0.05
    istan
    -0.05
    ibal
    -0.05
    ساء
    -0.05
     an
    -0.05
    ing
    -0.05
    POSITIVE LOGITS
    spflicht
    0.07
    天ä¹ĭ
    0.07
     Ùħتاب
    0.07
    elts
    0.06
    æĩµ
    0.06
    itulo
    0.06
    alisi
    0.06
    érité
    0.06
    ÑīноÑģÑĤÑĮ
    0.06
    赫
    0.06
    Activations Density 0.002%

    No Known Activations