© 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. 17576
    Prev
    Next
    INDEX
    Explanations

    percentage or specific dates

    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
    èĮĹ
    -0.05
     ÙĥÙĨ
    -0.05
    oose
    -0.05
    èį·
    -0.05
    æĦıå¤ĸ
    -0.05
    æ·»
    -0.05
    aq
    -0.05
    STRUCTIONS
    -0.05
    çİ°
    -0.05
    æĺĨ
    -0.05
    POSITIVE LOGITS
    ohl
    0.06
    YYY
    0.06
    æŃ¢è·Į
    0.06
    åѦæĬ¥
    0.06
    @",
    0.06
    althy
    0.06
    oger
    0.05
    нали
    0.05
    chy
    0.05
    estin
    0.05
    Activations Density 0.003%

    No Known Activations