© 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. 20207
    Prev
    Next
    INDEX
    Explanations

    POSW coins or similar technical terms

    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
    aska
    -0.06
    YES
    -0.06
    iniz
    -0.06
    åĴ§åĺ´
    -0.06
     Thing
    -0.06
    cj
    -0.06
    pend
    -0.06
    ÙĤÙĬ
    -0.06
    èĢĮåĩº
    -0.06
     Frame
    -0.06
    POSITIVE LOGITS
    宿
    0.05
    ampions
    0.05
    æĹłæĥħ
    0.05
    minster
    0.05
    голов
    0.05
    çIJīçĴĥ
    0.05
    extensions
    0.05
    庵
    0.05
    æľĢä¼Łå¤§çļĦ
    0.05
    	ext
    0.05
    Activations Density 0.006%

    No Known Activations