© 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. 22021
    Prev
    Next
    INDEX
    Explanations

    notable people or former list

    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
    ä¹ĭä¸ĢçļĦ
    -0.06
    eses
    -0.05
    ä¹ĭä¸Ģ
    -0.05
    aso
    -0.05
    æľ¬äºº
    -0.05
     poter
    -0.05
    odo
    -0.05
    çļĦä¸Ģ项
    -0.05
     gói
    -0.05
    æĿĤ
    -0.04
    POSITIVE LOGITS
    æĪ·æĻĵ
    0.07
    меÑģÑĤи
    0.06
    çł¥
    0.06
     indywidual
    0.06
    jú
    0.06
    使ä¹ĭ
    0.06
    åĬŁèĩ£
    0.06
    блÑĥ
    0.06
    arak
    0.06
     Urla
    0.06
    Activations Density 0.039%

    No Known Activations