© 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. 36227
    Prev
    Next
    INDEX
    Explanations

    describing countries and islands

    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
    å½ĵåľ°çļĦ
    -0.11
    åľ¨å½ĵåľ°
    -0.10
    æĹ¥æľ¬ãģ®
    -0.09
    çľ¼åīįçļĦ
    -0.09
    å½ĵåľ°äºº
    -0.09
     اÙĦصÙĬÙĨ
    -0.09
    çķ¶åľ°
    -0.09
    å½ĵåľ°
    -0.09
    .Local
    -0.09
    åī¥
    -0.09
    POSITIVE LOGITS
    çļĦ好
    0.10
    é«ĺéĢŁ
    0.10
    è¿ijäºĽ
    0.09
    ersh
    0.09
    æijĶ
    0.09
    åĽ½æ°ijç»ıæµİ
    0.09
    âį¨
    0.09
    æĸ½è¡Į
    0.08
     economy
    0.08
    immel
    0.08
    Activations Density 0.185%

    No Known Activations