© 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. 16619
    Prev
    Next
    INDEX
    Explanations

    order or rank

    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
     peng
    -0.05
     ob
    -0.05
     mot
    -0.05
     beur
    -0.05
    åĬĿ
    -0.05
    кÑĥÑĢа
    -0.05
     phóng
    -0.05
    cil
    -0.05
     tel
    -0.05
    wol
    -0.05
    POSITIVE LOGITS
    ingan
    0.06
    uchos
    0.06
    OSS
    0.06
    ersatz
    0.06
    ucker
    0.06
    ifar
    0.06
    é¡¿
    0.06
     Pivot
    0.06
    cko
    0.05
    acker
    0.05
    Activations Density 0.012%

    No Known Activations