© 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. 20559
    Prev
    Next
    INDEX
    Explanations

    commands or search parameters

    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
    认å®ļçļĦ
    -0.06
    åĴĮ社åĮº
    -0.06
    æ»ĭåij³
    -0.06
    åĴĮä¸ĸçķĮ
    -0.06
    è§ģ人
    -0.06
     ame
    -0.06
    licken
    -0.06
    ÑĮе
    -0.06
    认å®ļ
    -0.06
    è¿ĻèĤ¡
    -0.06
    POSITIVE LOGITS
    容
    0.06
    ontan
    0.06
     raya
    0.06
     til
    0.05
    便
    0.05
     toast
    0.05
    è¾ħåĬ©
    0.05
    éĢł
    0.05
    athon
    0.05
    ahead
    0.05
    Activations Density 0.005%

    No Known Activations