© 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. 21243
    Prev
    Next
    INDEX
    Explanations

    programming languages and frameworks

    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
    oren
    -0.07
    HING
    -0.06
    iaga
    -0.06
    å¦ĤæĹł
    -0.06
    favor
    -0.06
    åĽłä¸ºå®ĥ们
    -0.06
    æ³ķ
    -0.05
    à¸Īà¸į
    -0.05
    inder
    -0.05
    åľ¨éĩĮéĿ¢
    -0.05
    POSITIVE LOGITS
    ole
    0.05
    å¼łå¿Ĺ
    0.05
     central
    0.05
    loe
    0.05
     Central
    0.05
    æĪijä¸įæķ¢
    0.05
     Ers
    0.05
    ossa
    0.05
     awesome
    0.05
    unc
    0.05
    Activations Density 0.065%

    No Known Activations