© 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. 38696
    Prev
    Next
    INDEX
    Explanations

    list separators or conjunctions

    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
    éĤ£ä½į
    -0.10
    æĬĢæľ¯åĴĮ
    -0.09
    管çIJĨåĴĮ
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.08
    åĽĽäºĶ
    -0.08
    èĥ½åĬĽåĴĮ
    -0.08
    禽
    -0.08
    æľŁåĨħ
    -0.08
    è´¨éĩıåĴĮ
    -0.08
    åħ¨åĽ½
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³
    0.14
    æĢ»ä¹ĭ
    0.13
    以èĩ³äºİ
    0.12
    çĶļèĩ³æĺ¯
    0.12
    ãģĿãģĹãģ¦
    0.12
     tháºŃm
    0.12
    è¿ĻäºĽéĥ½æĺ¯
    0.11
    çŃīçŃī
    0.11
    ãģ¨ãģĦãģ£ãģŁ
    0.11
     etc
    0.11
    Activations Density 0.102%

    No Known Activations