© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17981
    Prev
    Next
    INDEX
    Explanations

    atheist or secular

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çķı
    -0.06
    å®ļ
    -0.06
     repr
    -0.06
    oton
    -0.06
    otypical
    -0.06
    zew
    -0.06
     disproportionately
    -0.06
    zze
    -0.06
    alej
    -0.06
    instanc
    -0.06
    POSITIVE LOGITS
     secular
    0.08
    æĭ¥æĬ±
    0.06
    è¿ĩ渡
    0.06
    æĪ·
    0.06
    ana
    0.06
     liberalism
    0.05
     atheists
    0.05
    åĬ¡å®ŀ
    0.05
     liberal
    0.05
     atheist
    0.05
    Activations Density 0.034%

    No Known Activations