© 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. 16659
    Prev
    Next
    INDEX
    Explanations

    moved

    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
    جد
    -0.06
    inach
    -0.06
    кÑĥÑĢо
    -0.06
    æĪĪå°Ķ
    -0.06
    obody
    -0.05
     oby
    -0.05
    没éĶĻ
    -0.05
    .Gradient
    -0.05
    Senin
    -0.05
    est
    -0.05
    POSITIVE LOGITS
    awl
    0.06
    寻
    0.06
     hơi
    0.05
    éĤ£ä¹Ī容æĺĵ
    0.05
    erge
    0.05
    åıijæī¬
    0.05
    Caps
    0.05
    æĺ¯åIJ¦åŃĺåľ¨
    0.05
    åľ¨åħ·ä½ĵ
    0.05
    erman
    0.05
    Activations Density 0.008%

    No Known Activations