© 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. 18303
    Prev
    Next
    INDEX
    Explanations

    possess the gift

    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
    utte
    -0.06
    epe
    -0.06
    æĥ³åĪ°äºĨ
    -0.06
    ноÑĢа
    -0.06
    好ä¸ĢçĤ¹
    -0.06
    боÑĢо
    -0.06
    åĢĴéľī
    -0.05
     ÙĨاب
    -0.05
    ủ
    -0.05
    رع
    -0.05
    POSITIVE LOGITS
     univers
    0.06
    åħ¶è¡Į为
    0.05
    inox
    0.05
     behaves
    0.05
    iny
    0.05
    è¿Ļç§įè¡Į为
    0.05
     Bef
    0.05
    å¤ĸæĸĩ
    0.05
    0.05
    Universal
    0.05
    Activations Density 0.001%

    No Known Activations