© 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. 19146
    Prev
    Next
    INDEX
    Explanations

    install, pip, .io, github

    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
    éĽ
    -0.05
    å¾¹
    -0.05
     forcefully
    -0.05
    ool
    -0.05
    etest
    -0.05
    大èĥľ
    -0.05
     proces
    -0.05
    侧éĩį
    -0.05
    REEN
    -0.05
    /oct
    -0.05
    POSITIVE LOGITS
    assa
    0.07
     aspiration
    0.06
    次åħĥ
    0.06
    .flat
    0.06
    iman
    0.06
    åIJįä¸ĭ
    0.06
    è¿Ļé¦ĸè¯Ĺ
    0.06
    kÄģ
    0.06
    æľīéģĵ
    0.06
    eliz
    0.06
    Activations Density 0.019%

    No Known Activations