© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19141
    Prev
    Next
    INDEX
    Explanations

    in words following determiners

    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
    itud
    -0.07
    famil
    -0.07
    голов
    -0.07
     frank
    -0.06
     ÄĮesk
    -0.06
    ãĤĴåĽ³
    -0.06
    Äĥr
    -0.06
    asic
    -0.06
    iare
    -0.06
    åĽłä¸ºå®ĥ
    -0.06
    POSITIVE LOGITS
    é¹
    0.06
    æĺ¯è°ģ
    0.05
    åĬ¨
    0.05
    boten
    0.05
    lest
    0.05
    gether
    0.04
    ctor
    0.04
    åłª
    0.04
    REAM
    0.04
    elli
    0.04
    Activations Density 0.026%

    No Known Activations