© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21234
    Prev
    Next
    INDEX
    Explanations

    grew up in

    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
    èIJ¥åĪ©
    -0.09
    å¹³æŶ
    -0.08
    achi
    -0.08
    æıIJæĹ©
    -0.08
    æıIJåīį
    -0.08
    æī¾åĩĨ
    -0.08
    çĭĻ
    -0.08
     Cambridge
    -0.08
    æĪij们çİ°åľ¨
    -0.08
    å®īæĬļ
    -0.08
    POSITIVE LOGITS
     sme
    0.09
    éĻĶ
    0.09
    éĺ³åħī
    0.08
    åģ¥åħ¨
    0.08
    ä»Ģä¹Īæł·
    0.08
    åŃ
    0.08
    æĹłæīĢè°ĵ
    0.08
    éķĽ
    0.08
    طة
    0.08
    èĤ¡
    0.08
    Activations Density 0.052%

    No Known Activations