© 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. 18248
    Prev
    Next
    INDEX
    Explanations

    group of people

    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
     sumar
    -0.07
    inggal
    -0.06
    riu
    -0.06
     sigur
    -0.06
    estin
    -0.06
    æµģ线
    -0.06
    ä¹ĭæīĢ
    -0.06
    skal
    -0.06
    à¹Į
    -0.06
    ç©©
    -0.06
    POSITIVE LOGITS
    ingles
    0.06
    av
    0.06
    ingly
    0.06
    ses
    0.05
    utenberg
    0.05
    pect
    0.05
    é¦ĸ
    0.05
    pires
    0.05
     ca
    0.05
    iven
    0.05
    Activations Density 0.011%

    No Known Activations