© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22379
    Prev
    Next
    INDEX
    Explanations

    further ado

    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
    Negative Logits
    åĴª
    -0.07
    enticated
    -0.06
    çļĦçĭĢæ³ģ
    -0.06
    thus
    -0.06
    ä»Ģä¹ĪæĥħåĨµ
    -0.06
    춤
    -0.06
    urtles
    -0.06
    çļĦæĸ¹æ¡Ī
    -0.06
    (mappedBy
    -0.05
    çļĦéģİç¨ĭ
    -0.05
    POSITIVE LOGITS
     Thorn
    0.05
    ä¸į管
    0.05
    коÑģÑĤÑĮÑİ
    0.05
    æĶ¾åľ¨å¿ĥä¸Ĭ
    0.05
    åĪĨä¹ĭ
    0.05
     either
    0.05
    éĩįè¦ģæĢ§
    0.05
    mern
    0.05
    ill
    0.04
     Blok
    0.04
    Activations Density 0.001%

    No Known Activations