© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17228
    Prev
    Next
    INDEX
    Explanations

    team of

    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
     пеÑĢе
    -0.06
     Ùħا
    -0.06
    annon
    -0.05
    neider
    -0.05
    IMI
    -0.05
    æī§è¡Įå®ĺ
    -0.05
     اÙĦÙĨÙģ
    -0.05
    imate
    -0.05
    ãģĦãģł
    -0.05
    berte
    -0.05
    POSITIVE LOGITS
     likely
    0.06
     Ñīоб
    0.06
    åŁºå±Ĥåħļ建
    0.05
    ä»İæѤ
    0.05
     ultimately
    0.05
    ürzt
    0.05
    áž
    0.05
    ä¸īçŃī
    0.05
    å®īåħ¨æĢ§åĴĮ
    0.05
    å½ĵä¹ĭ
    0.05
    Activations Density 0.001%

    No Known Activations