© 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. 56014
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

    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
    åĪº
    -0.09
    çĤ¹äº®
    -0.09
    ä¸¤åĽ½
    -0.09
    æ±īè¯Ń
    -0.09
     Yuan
    -0.09
    åĽ½åĨħå¸Ĥåľº
    -0.09
    ä¸ĢæľŁ
    -0.09
    绢
    -0.09
    ouch
    -0.09
    éļĶ
    -0.09
    POSITIVE LOGITS
    éĿ¢è²Į
    0.09
     Duke
    0.08
    æŃ£å½ĵ
    0.08
    cole
    0.08
    ä½ŀ
    0.08
    åĩĭ
    0.08
    åĩºçīĪ社
    0.08
    ãģķãģĪ
    0.08
    å®Įå¤ĩ
    0.08
    è¶Ĭ
    0.08
    Activations Density 0.050%

    No Known Activations