© 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. 27152
    Prev
    Next
    INDEX
    Explanations

    plant suffixes

    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
    è¦ģåѦä¼ļ
    -0.10
    çĸı导
    -0.09
     muj
    -0.09
    åĬ³
    -0.09
     Dra
    -0.08
    äºĶæľĪ
    -0.08
    æĶ¹èī¯
    -0.08
    ppard
    -0.08
    稿
    -0.08
    èĤĿèĦı
    -0.08
    POSITIVE LOGITS
    æĨĻ
    0.09
    DialogTitle
    0.09
    粤港澳
    0.09
     kn
    0.09
    -covered
    0.08
    ease
    0.08
    ¾ç¤º
    0.08
    æ¼
    0.08
    ä¾ĭå¤ĸ
    0.08
    ees
    0.08
    Activations Density 0.033%

    No Known Activations