© 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. 61294
    Prev
    Next
    INDEX
    Explanations

    love and praise

    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
     Chill
    -0.09
    Offsets
    -0.09
    æĦļ
    -0.09
    çļĦçľ¼
    -0.09
    è¯ķè¡Į
    -0.08
     Mund
    -0.08
    èĥĨ
    -0.08
    åıĸè¯ģ
    -0.08
     بت
    -0.08
    ffset
    -0.08
    POSITIVE LOGITS
    å¾ħéģĩ
    0.10
    çĶŁåij½
    0.10
    æ»ĭ润
    0.09
    å¾Ĺä¸įåĪ°
    0.09
    æ·ĭ
    0.09
    åĪĨæĺİ
    0.09
    åħħ足
    0.09
    ä¹¾
    0.09
    åħ³æĢĢ
    0.09
    tabs
    0.09
    Activations Density 0.061%

    No Known Activations