© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19680
    Prev
    Next
    INDEX
    Explanations

    we followed by a verb

    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
    ç¢Į
    -0.06
    aty
    -0.05
    æIJŀ
    -0.05
    ards
    -0.05
    ÑģÑĤоÑı
    -0.05
    صÙģ
    -0.05
     turb
    -0.05
    alap
    -0.05
    /do
    -0.05
    ÙħÙĬØ©
    -0.05
    POSITIVE LOGITS
    ÑģÑı
    0.08
    nya
    0.07
    Æ°á»Ľc
    0.06
    piar
    0.06
    êµīìŀ¥
    0.06
    Æ°Æ¡ng
    0.06
    гаÑı
    0.06
    äºİä¸Ģ
    0.06
    unable
    0.06
    zust
    0.06
    Activations Density 0.018%

    No Known Activations