© 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. 20422
    Prev
    Next
    INDEX
    Explanations

    input class element

    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
    οÏħÏģγ
    -0.06
    éĢŀ
    -0.06
     Unlimited
    -0.06
    åı£çļĦ
    -0.06
    æĮī
    -0.05
    çĴĭ
    -0.05
    ä¹³
    -0.05
    æľĪèĩ³ä»Ĭ
    -0.05
    оÑĤов
    -0.05
    ÑĤкÑĥ
    -0.05
    POSITIVE LOGITS
    chow
    0.06
     glazed
    0.06
     Throw
    0.05
    æĢģ度åĴĮ
    0.05
     kolei
    0.05
     паÑģ
    0.05
    round
    0.05
    ienza
    0.05
    大åıĺ
    0.05
    Story
    0.05
    Activations Density 0.008%

    No Known Activations