© 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. 52012
    Prev
    Next
    INDEX
    Explanations

    lists of items and topics

    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
    åħĪæĺ¯
    -0.10
    æĮīä¸ĭ
    -0.09
    ä¸Ģ侧
    -0.08
    è°ĥæŁ¥æĺ¾ç¤º
    -0.08
    ä¸Ģè§Ĵ
    -0.08
    iez
    -0.08
    oley
    -0.08
    åĪĨ为
    -0.08
    obar
    -0.08
    åĬłåĪĨ
    -0.08
    POSITIVE LOGITS
    /or
    0.18
     etc
    0.17
    ãģĿãģĹãģ¦
    0.16
     tháºŃm
    0.15
    ä¹ĥèĩ³
    0.14
    çĶļèĩ³æĺ¯
    0.14
    以åıĬ
    0.14
    etc
    0.13
    acles
    0.13
    çŃīæĸ¹éĿ¢çļĦ
    0.12
    Activations Density 0.335%

    No Known Activations