© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20085
    Prev
    Next
    INDEX
    Explanations

    equator, poles, latitude, tropics, hemisphere, equinox

    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
    ä¸ĭ乡
    -0.10
     Westbrook
    -0.10
    åłķ
    -0.09
    éĻĮ
    -0.09
    å¸Ĥ级
    -0.09
    åĭĴ
    -0.09
    BorderStyle
    -0.09
    åħ¨å¸Ĥ
    -0.08
    åįĹ京å¸Ĥ
    -0.08
    êµ°
    -0.08
    POSITIVE LOGITS
    åľ°åĮºçļĦ
    0.11
    åľ°åĮº
    0.11
    纬
    0.11
     lat
    0.10
     regions
    0.10
    èķī
    0.09
    åľ°åŁŁ
    0.09
    åĴĮåľ°åĮº
    0.09
    åįĹåĮĹ
    0.09
    åľ°åįĢ
    0.09
    Activations Density 0.043%

    No Known Activations