© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31131
    Prev
    Next
    INDEX
    Explanations

    philosophy, religion, and specific origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ming
    -0.09
    asant
    -0.09
    寥
    -0.09
    sed
    -0.09
    enge
    -0.08
    åħ¬ç«ĭ
    -0.08
    ngx
    -0.08
    ä»ĭåħ¥
    -0.08
    ann
    -0.08
    USA
    -0.08
    POSITIVE LOGITS
    壬
    0.10
    欺è¯Ī
    0.10
    åıĸæ¶Ī
    0.09
    延ç»Ń
    0.09
    éĹ®éģĵ
    0.09
    .tell
    0.09
    欺éªĹ
    0.08
    é£
    0.08
     Tobacco
    0.08
    åħ±å»º
    0.08
    Activations Density 0.051%

    No Known Activations