© 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. 17147
    Prev
    Next
    INDEX
    Explanations

    sharing links or information

    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
    avn
    -0.06
    tern
    -0.06
    Ú¯ÛĮ
    -0.05
    åĬŁ
    -0.05
    çłĶ
    -0.05
    è£ħåľ¨
    -0.05
    æĿIJ
    -0.05
     onda
    -0.05
    å½ĵäºĭ人çļĦ
    -0.05
    aine
    -0.05
    POSITIVE LOGITS
    o
    0.06
    ju
    0.06
    æĿ¥å¤ĦçIJĨ
    0.05
    oja
    0.05
    ç¼ĸçīĪ
    0.05
    sha
    0.05
    ajar
    0.05
     Sie
    0.05
    ya
    0.05
    çļĦä¸ĢæīĢ
    0.05
    Activations Density 0.004%

    No Known Activations