© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21785
    Prev
    Next
    INDEX
    Explanations

    professional titles and roles

    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
    ego
    -0.09
    dia
    -0.08
     ourselves
    -0.08
    å±ħçĦ¶
    -0.08
    æ¯Ķå¦Ĥ
    -0.08
    fest
    -0.08
    tas
    -0.08
    渺
    -0.08
    ä¸įä¸Ģæł·çļĦ
    -0.08
    Datas
    -0.08
    POSITIVE LOGITS
    åħ¼
    0.15
    åIJĮæĹ¶ä¹Łæĺ¯
    0.12
    èģĮåĬ¡
    0.10
    æľŁéĹ´
    0.10
    åĴ½åĸī
    0.10
    åµĮ
    0.10
    èģĮä½į
    0.10
    åIJĮæĻĤãģ«
    0.10
     ëıĻìĭľìĹIJ
    0.10
    å¤ļå¹´çļĦ
    0.10
    Activations Density 0.184%

    No Known Activations