© 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. 19816
    Prev
    Next
    INDEX
    Explanations

    `Get` or `return` programming functions

    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
    alde
    -0.06
    绣æĪĺéĥ¨
    -0.06
    otto
    -0.06
    attle
    -0.06
     Nielsen
    -0.05
    eus
    -0.05
    atto
    -0.05
    utas
    -0.05
    ä¹ĸ
    -0.05
    å°¼å°Ķ
    -0.05
    POSITIVE LOGITS
    emy
    0.06
    ständ
    0.06
    elps
    0.05
    orea
    0.05
    ุà¸ģ
    0.05
    åĬĽãģ§
    0.05
    å¤ļæł·çļĦ
    0.05
     Din
    0.05
    ุà¹Īม
    0.05
    åıªæľīè¿Ļæł·
    0.05
    Activations Density 0.003%

    No Known Activations