© 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. 20056
    Prev
    Next
    INDEX
    Explanations

    contact, health, communication

    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
    Ø®ÙĨ
    -0.06
    éĢģ
    -0.06
    ai
    -0.06
    acked
    -0.06
    æĴ®
    -0.05
    acking
    -0.05
    Law
    -0.05
    åѦä¸ĵä¸ļ
    -0.05
     GSL
    -0.05
     Daarom
    -0.05
    POSITIVE LOGITS
    anaman
    0.06
    egis
    0.05
     Tob
    0.05
    æ¬
    0.05
    à¹Ģà¸ķ
    0.05
    boek
    0.05
    valueOf
    0.05
    irteen
    0.05
    æ¡IJ
    0.05
    æĦıå¢ĥ
    0.05
    Activations Density 0.111%

    No Known Activations