© 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. 63457
    Prev
    Next
    INDEX
    Explanations

    process through ongoing operations

    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
    åıĪèĥ½
    -0.10
    æ²ĥ
    -0.09
    åĪ°æŶåĢĻ
    -0.09
    尽快
    -0.09
     Heading
    -0.08
    ependency
    -0.08
    omp
    -0.08
     Pompeo
    -0.08
    åij¼åºĶ
    -0.08
    atics
    -0.08
    POSITIVE LOGITS
    严
    0.12
    åݳãģĹãģĦ
    0.11
    ä¸¥æł¼çļĦ
    0.09
    ä¸¥æł¼
    0.09
    .locals
    0.09
    å½ĵåľ°æĶ¿åºľ
    0.09
    èĭĽ
    0.09
    åİĨç»ı
    0.09
    adius
    0.08
    ç»ıè¿ĩ
    0.08
    Activations Density 0.024%

    No Known Activations