© 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. 21004
    Prev
    Next
    INDEX
    Explanations

    sql select statements

    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
    èĴĤ
    -0.06
    ï¸ı
    -0.06
    à¸ģัà¸Ļ
    -0.05
    usas
    -0.05
    çļĦ顺åºı
    -0.05
    ç¦ģçĶ¨
    -0.05
    edList
    -0.05
    ä¸įå¼Ģ
    -0.05
    illard
    -0.05
    ØŃاÙħ
    -0.05
    POSITIVE LOGITS
    itud
    0.06
    äºĮåįģåĽĽ
    0.05
     Ø®ÙĪدش
    0.05
    Hotline
    0.05
     measurable
    0.05
    portion
    0.05
    æĹ©äºĽ
    0.05
    trop
    0.05
    æľ¬èģĮå·¥ä½ľ
    0.05
    prite
    0.05
    Activations Density 0.018%

    No Known Activations