© 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. 22502
    Prev
    Next
    INDEX
    Explanations

    binary choice or states

    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
     Same
    -0.05
    etas
    -0.05
    amel
    -0.05
     Tar
    -0.05
    U
    -0.05
    éĿ¢çĽ¸
    -0.05
     same
    -0.05
    缸åIJĮ
    -0.05
    phant
    -0.05
    NI
    -0.05
    POSITIVE LOGITS
     contrasting
    0.08
    主è¦ģåĪĨ为
    0.08
     either
    0.08
    è¦ģä¹Ī
    0.08
     Either
    0.08
    两大
    0.08
     dich
    0.07
    ondo
    0.07
    åĪĨ为
    0.07
    either
    0.07
    Activations Density 0.134%

    No Known Activations