© 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. 19372
    Prev
    Next
    INDEX
    Explanations

    first column

    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
    èĢħä¼ĺåħĪ
    -0.07
    istor
    -0.07
    à¸ķร
    -0.07
    ثة
    -0.07
    zik
    -0.07
    зÑĭ
    -0.07
    zó
    -0.07
    istr
    -0.07
    quip
    -0.06
    ation
    -0.06
    POSITIVE LOGITS
    s
    0.09
    ات
    0.06
    some
    0.06
    say
    0.06
    äºĭæĥħ
    0.05
    åĴĮåŃ¦ä¹ł
    0.05
    ri
    0.05
     Hayden
    0.05
     some
    0.05
    skal
    0.05
    Activations Density 0.027%

    No Known Activations