© 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. 16613
    Prev
    Next
    INDEX
    Explanations

    conditional preprocessor directives

    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
    åıĬåĪ©æģ¯
    -0.07
    slaught
    -0.07
    èIJ¥åķĨ
    -0.07
    ibling
    -0.07
    èī²åĪĹ
    -0.07
    宫åĨħ
    -0.07
    ondre
    -0.06
    borgen
    -0.06
    arach
    -0.06
    regn
    -0.06
    POSITIVE LOGITS
    ijo
    0.06
    vs
    0.06
    azan
    0.05
    ect
    0.05
    vy
    0.05
    åĩį
    0.05
    ÛĮت
    0.05
    ünen
    0.05
    д
    0.05
    utable
    0.05
    Activations Density 0.004%

    No Known Activations