© 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. 22576
    Prev
    Next
    INDEX
    Explanations

    loading or building

    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
    ald
    -0.07
    ü
    -0.06
    å¾ģ
    -0.06
    vez
    -0.06
    ìĪł
    -0.06
    enc
    -0.06
    è¦ģä¹Īæĺ¯
    -0.06
    hold
    -0.06
     Either
    -0.05
    ath
    -0.05
    POSITIVE LOGITS
    даÑĩи
    0.06
    ilers
    0.06
    idem
    0.06
    quisites
    0.06
    rer
    0.06
     رØŃ
    0.06
    xil
    0.06
    iculos
    0.05
    cassert
    0.05
    imbing
    0.05
    Activations Density 0.018%

    No Known Activations