© 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. 18828
    Prev
    Next
    INDEX
    Explanations

    questions and lists

    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
    verk
    -0.06
    ocity
    -0.06
    λεγ
    -0.06
     true
    -0.06
    ä¸Ģå¸Ĩ
    -0.05
    unde
    -0.05
     Foley
    -0.05
     ges
    -0.05
    RootElement
    -0.05
    ä¸įä½ıçļĦ
    -0.05
    POSITIVE LOGITS
    ç§
    0.06
    æģ°æģ°
    0.05
     zim
    0.05
     nastav
    0.05
     Britann
    0.05
     commod
    0.05
    ÙģاÙĤ
    0.05
     precis
    0.05
     compost
    0.05
    ãģĹãģı
    0.05
    Activations Density 0.002%

    No Known Activations