© 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. 21221
    Prev
    Next
    INDEX
    Explanations

    and followed by contrasting conjunctions

    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
    汪æ´ĭ
    -0.05
     compliment
    -0.05
     following
    -0.05
    iums
    -0.05
    ä½Ĩåħ¶
    -0.05
    following
    -0.05
    osi
    -0.05
    çģµ
    -0.05
    edr
    -0.05
    ä½Ĩä¸įéĻIJäºİ
    -0.05
    POSITIVE LOGITS
    ละ
    0.06
     malah
    0.06
    ä¸Ĭä¸ĭæĸĩ
    0.05
    æĿĥåĴĮ
    0.05
    è¿ĩç¨ĭåĴĮ
    0.05
    èĮĥåĽ´åĴĮ
    0.05
    amik
    0.05
    wijk
    0.05
    aires
    0.05
    æĥħåĨµåĴĮ
    0.05
    Activations Density 0.038%

    No Known Activations