© 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. 17797
    Prev
    Next
    INDEX
    Explanations

    health benefits and medicinal properties

    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
    rej
    -0.08
    verka
    -0.07
    veri
    -0.07
     اÙĦصاد
    -0.07
     oynay
    -0.07
    otur
    -0.07
     indire
    -0.07
    åıĺåĮĸæĥħåĨµ
    -0.07
    earing
    -0.07
    antemente
    -0.06
    POSITIVE LOGITS
    nt
    0.05
    åĿĽ
    0.05
    udent
    0.05
     supported
    0.05
    /
    0.05
     covered
    0.05
     U
    0.05
    us
    0.05
    Supported
    0.05
    faf
    0.05
    Activations Density 0.030%

    No Known Activations