© 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. 19845
    Prev
    Next
    INDEX
    Explanations

    data and its context

    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
    å¦Ĥåħ¶
    -0.05
    isma
    -0.05
    ABCDE
    -0.05
    idental
    -0.05
     оÑĤо
    -0.05
    天水
    -0.05
     com
    -0.05
    æ¢Ń
    -0.05
    born
    -0.05
    codec
    -0.05
    POSITIVE LOGITS
     تØŃ
    0.06
    åĮĸ管çIJĨ
    0.06
     pewnoÅĽciÄħ
    0.06
    æ¯Ļ
    0.06
    ejo
    0.06
    ardy
    0.06
    æĢ§èĥ½çļĦ
    0.05
    åIJ¹ãģį
    0.05
    atron
    0.05
    èĤĺ
    0.05
    Activations Density 0.034%

    No Known Activations