© 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. 51321
    Prev
    Next
    INDEX
    Explanations

    US states and cities

    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
    æľīæľºç»ĵåIJĪ
    -0.09
    æĿŃå·ŀå¸Ĥ
    -0.08
    åºIJ
    -0.08
     Utah
    -0.08
     Ontario
    -0.08
    æ¹ĥ
    -0.08
    ete
    -0.08
    åħĢ
    -0.08
     Palo
    -0.08
    æ²Ĥ
    -0.07
    POSITIVE LOGITS
    åįĹéĿŀ
    0.11
    磺
    0.10
    ä¸īæĺŁ
    0.10
    èįĨ
    0.09
     Clemson
    0.09
    èij¡
    0.09
     Charleston
    0.09
    itar
    0.09
    è¥Ħ
    0.09
    åĩī
    0.09
    Activations Density 0.134%

    No Known Activations