© 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. 17713
    Prev
    Next
    INDEX
    Explanations

    equal opportunity employer or election

    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
    acent
    -0.07
    iface
    -0.06
     им
    -0.06
    apel
    -0.06
    artig
    -0.06
    ç¼ĸè¾ijäºİ
    -0.06
    æݧ
    -0.06
     Map
    -0.06
    åħįçĸ«åĬŁèĥ½
    -0.06
    appa
    -0.06
    POSITIVE LOGITS
    说å¾Ĺ
    0.06
    nä
    0.05
    说è¦ģ
    0.05
    æĬij
    0.05
    æľºä¼ļ
    0.05
    strstr
    0.05
    纹
    0.05
     Opport
    0.05
    age
    0.05
    var
    0.05
    Activations Density 0.001%

    No Known Activations