© 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. 17148
    Prev
    Next
    INDEX
    Explanations

    technological or musical advancements

    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
    u
    -0.06
    lement
    -0.06
    ally
    -0.06
    ward
    -0.06
    istor
    -0.06
    urg
    -0.06
    ort
    -0.06
    urger
    -0.06
    all
    -0.05
    ä¸Ĭ
    -0.05
    POSITIVE LOGITS
    ness
    0.08
    enne
    0.06
    maz
    0.06
    ITCH
    0.06
    nya
    0.06
    çļĦ
    0.06
    minus
    0.06
    reur
    0.06
    ical
    0.06
    клÑİÑĩа
    0.06
    Activations Density 0.066%

    No Known Activations