© 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. 21280
    Prev
    Next
    INDEX
    Explanations

    ultramicrotomy, autotype, print edition

    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
    æŁIJ
    -0.05
    emann
    -0.05
    æŁIJ个
    -0.05
    æŁIJä¸Ģ个
    -0.05
    æºľ
    -0.05
    ìłģìľ¼ë¡ľ
    -0.05
    izer
    -0.05
    иÑĦ
    -0.05
    lest
    -0.05
    ÙĥرÙħ
    -0.05
    POSITIVE LOGITS
     shortfall
    0.07
     Bén
    0.06
    даÑĩа
    0.06
    æı½
    0.06
    trys
    0.06
     voks
    0.06
    éĺľ
    0.06
    æľīç»Ħç»ĩ
    0.06
    tat
    0.06
     busted
    0.06
    Activations Density 0.001%

    No Known Activations