© 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. 50963
    Prev
    Next
    INDEX
    Explanations

    global warming

    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
    AMS
    -0.10
    aps
    -0.10
    稷
    -0.09
    ams
    -0.09
    AIL
    -0.09
    igm
    -0.09
    spath
    -0.09
    们çļĦ
    -0.09
    amar
    -0.09
    饱满
    -0.09
    POSITIVE LOGITS
    è¶ĭåĬ¿
    0.10
    stoff
    0.09
    çݰ象
    0.08
    داÙĨ
    0.08
    èĽŃ
    0.08
    orphic
    0.08
     اÙĦعاÙĦÙħÙĬ
    0.08
    è°ª
    0.08
    /Linux
    0.08
    第äºĮ天
    0.08
    Activations Density 0.012%

    No Known Activations