© 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. 1735
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide concentration

    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
    зÑĭ
    -0.09
    为人
    -0.09
    NDER
    -0.09
    æĥĩ
    -0.08
    æ¡Ī
    -0.08
     cross
    -0.08
     pan
    -0.08
    çļĦè®°å¿Ĩ
    -0.08
    çļĦä¸Ģ大
    -0.08
    åı¯ä¸įæĺ¯
    -0.08
    POSITIVE LOGITS
    endale
    0.10
    lemn
    0.10
    ledge
    0.09
    orest
    0.09
    åºķæ°Ķ
    0.09
    ä¿¡è´·
    0.09
    以åħį
    0.09
     Phụ
    0.09
    _trees
    0.09
     ÑįкÑģ
    0.09
    Activations Density 0.058%

    No Known Activations