© 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. 55956
    Prev
    Next
    INDEX
    Explanations

    vegetables and animals

    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
     Zus
    -0.10
    å¹ķ
    -0.09
    aki
    -0.09
    éľİ
    -0.09
    润æ»ijæ²¹
    -0.09
    ç¦Ħ
    -0.09
    vais
    -0.09
    usher
    -0.09
    çĶļèĩ³è¿ĺ
    -0.08
     Leigh
    -0.08
    POSITIVE LOGITS
    æŀ¢çº½
    0.09
    اÙģت
    0.09
    åĪĨæĪIJ
    0.09
    åİ»æİī
    0.08
    anth
    0.08
    infos
    0.08
    mob
    0.08
    IBLE
    0.08
    溽
    0.08
    åŃIJå¼¹
    0.08
    Activations Density 0.040%

    No Known Activations