© 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. 21102
    Prev
    Next
    INDEX
    Explanations

    close to others

    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
    åĹŁ
    -0.10
    MOTE
    -0.10
    çĽij
    -0.09
    æģ¸
    -0.09
    hair
    -0.09
    ä¹ĭåŁİ
    -0.09
    criptor
    -0.09
    æĪĺçķ¥åIJĪä½ľ
    -0.09
    欢åij¼
    -0.09
     Ñģебе
    -0.09
    POSITIVE LOGITS
    è¿Ļä¹Łæĺ¯
    0.11
    è¿Ļæĺ¯
    0.11
    è¿Ļæĺ¯ä¸Ģ个
    0.10
    è¿ĻäºĽéĥ½æĺ¯
    0.10
    è¿Ļå°±æĺ¯
    0.09
    è¿Ļæīįæĺ¯
    0.09
    è¿Ļæĺ¯åĽłä¸º
    0.09
    è¶Ĭæĺ¯
    0.09
    è¿Ļæĺ¯æĪij们
    0.08
    è¿Ļæĺ¯ä¸Ģç§į
    0.08
    Activations Density 0.090%

    No Known Activations