© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19735
    Prev
    Next
    INDEX
    Explanations

    in to a

    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
    ocks
    -0.07
    voja
    -0.06
    两èĢħ
    -0.05
    uler
    -0.05
    åĪº
    -0.05
    ero
    -0.05
    äºĮèĢħ
    -0.05
    ores
    -0.05
    eta
    -0.05
    orns
    -0.05
    POSITIVE LOGITS
    æŁIJä¸Ģ个
    0.07
    æŁIJ个
    0.07
    æŁIJ
    0.07
    æŁIJçļĦ
    0.07
    ä»İä¸Ģ个
    0.06
    æŁIJä¸Ģ
    0.06
     né
    0.06
    /*/
    0.06
    forg
    0.06
    对åºĶçļĦ
    0.06
    Activations Density 0.121%

    No Known Activations