© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16826
    Prev
    Next
    INDEX
    Explanations

    market and consumer demands

    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
    oppi
    -0.06
    使çĶ¨çļĦ
    -0.06
    æĿ¥ä¸įåıĬ
    -0.06
    çĶ¨çļĦ
    -0.06
    使çĶ¨æĥħåĨµ
    -0.05
    使çĶ¨æĸ¹æ³ķ
    -0.05
    oon
    -0.05
    ilo
    -0.05
    åĿĩåĮĢ
    -0.05
    éĥİ
    -0.05
    POSITIVE LOGITS
    ç¼
    0.06
    åĴĮçݯå¢ĥ
    0.06
     environmentally
    0.06
     Leg
    0.06
    ugend
    0.06
    leg
    0.06
    terer
    0.06
    viron
    0.06
     Svensk
    0.05
    corre
    0.05
    Activations Density 0.017%

    No Known Activations