© 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. 19870
    Prev
    Next
    INDEX
    Explanations

    dental, medical, and college care

    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
     ofre
    -0.06
    ç±į
    -0.06
     Borders
    -0.06
     ür
    -0.06
    çļĦæŃ»
    -0.06
    undu
    -0.06
    æŃ»
    -0.06
    yiz
    -0.06
    åĵĹ
    -0.06
    ello
    -0.06
    POSITIVE LOGITS
    éĹ®é¢ĺçļĦ
    0.05
    离家
    0.05
    rices
    0.05
    æĪijä¸Ģå®ļä¼ļ
    0.05
    íĵ¨
    0.05
    éĴ£éĩij
    0.05
    inite
    0.05
    åĴĮå¼ł
    0.05
     Monta
    0.05
    éĺ»
    0.05
    Activations Density 0.008%

    No Known Activations