© 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. 18739
    Prev
    Next
    INDEX
    Explanations

    lighthearted, irreverent, humour

    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
    æģµ
    -0.07
    æĭĻ
    -0.06
    éķ¿ç©º
    -0.06
    æĩĴ人
    -0.06
    æĥł
    -0.06
    imak
    -0.06
    åºŁçī©
    -0.05
    伶
    -0.05
    elek
    -0.05
    ÙĦÙĬØ©
    -0.05
    POSITIVE LOGITS
    auft
    0.05
    ival
    0.05
     concurrent
    0.05
    éĿ¢åIJij社ä¼ļ
    0.05
    รัà¸ķ
    0.05
    å¦Ĭ
    0.05
     delicato
    0.05
    é¦ĸ
    0.05
    å¼ĤåĬ¨
    0.05
    æĮĩ导æĢĿæĥ³
    0.05
    Activations Density 0.003%

    No Known Activations