© 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. 20645
    Prev
    Next
    INDEX
    Explanations

    quotation openings

    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
    æĥħåĨµè¿Ľè¡Į
    -0.09
    vier
    -0.09
    çĶļèĩ³
    -0.09
    åĪ¶æĪIJ
    -0.09
    åĬŁè¯¾
    -0.08
    åĬĿ
    -0.08
    Ñĭми
    -0.08
    è¿ĺå°Ĩ
    -0.08
    åĩłä¹İæĺ¯
    -0.08
    ainer
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķä¸Ģ个
    0.10
    ä¸ĩåĪĨ
    0.10
    èį£å¹¸
    0.09
     ÑıвлÑı
    0.09
    è¡·å¿ĥ
    0.09
    etsk
    0.09
    .Microsoft
    0.09
    åĩĮ
    0.08
    åĬłåħ¥
    0.08
    .opensource
    0.08
    Activations Density 0.026%

    No Known Activations