© 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. 27672
    Prev
    Next
    INDEX
    Explanations

    indoor air quality and concentration

    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
    æĸĩä¸Ń
    -0.10
    ä¸Ģå¦Ĥ
    -0.10
     Brewer
    -0.09
    æĶ¯æŀ¶
    -0.08
    ä¸įè¿ľ
    -0.08
    缺åı£
    -0.08
    usta
    -0.08
     Jets
    -0.08
    缺失
    -0.08
    丢失
    -0.08
    POSITIVE LOGITS
    访
    0.10
    家çĶµ
    0.10
    家å±ħ
    0.09
    åĩĢåĮĸ
    0.09
    OOT
    0.09
    空æ°ĶåĩĢåĮĸ
    0.08
    èIJĮ
    0.08
    æİĴæ¯Ĵ
    0.08
    åĬ«
    0.08
    åIJĬ顶
    0.08
    Activations Density 0.069%

    No Known Activations