© 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. 20349
    Prev
    Next
    INDEX
    Explanations

    architects and architecture

    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
    جات
    -0.07
    çĸ±
    -0.07
    æį»
    -0.06
    ÑĥÑī
    -0.06
    ovin
    -0.06
    æ´»çļĦ
    -0.06
    ÑģÑĤÑı
    -0.06
    çļĦä¿¡
    -0.06
    iedades
    -0.06
    ctors
    -0.06
    POSITIVE LOGITS
    æĸ¹èĪŁ
    0.05
    æľĢæĸ°è¯Ħ论
    0.05
     podium
    0.05
    mdl
    0.05
    æľīæķĪæݧåĪ¶
    0.05
     internally
    0.05
     individuelles
    0.05
     Hawks
    0.05
    ãĤ·ãĥ³ãĥĹãĥ«ãģª
    0.05
    uri
    0.05
    Activations Density 0.019%

    No Known Activations