© 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. 3397
    Prev
    Next
    INDEX
    Explanations

    audience

    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
     verbal
    -0.09
    ÐĺÐĿ
    -0.09
    è¨Ģ
    -0.09
    请大家
    -0.09
    è§ĦåĪĴ
    -0.09
    å¸ĮæľĽå¤§å®¶
    -0.08
    åĪ¶å®ļäºĨ
    -0.08
     Greenwood
    -0.08
     зан
    -0.08
    è¨Ģè¯Ń
    -0.08
    POSITIVE LOGITS
     audience
    0.22
     audiences
    0.20
    åıĹä¼Ĺ
    0.20
    åIJ¬ä¼Ĺ
    0.20
    è§Ĥä¼Ĺ
    0.19
     Audience
    0.18
    åıįé¦Ī
    0.11
     اÙĦجÙħÙĩÙĪر
    0.11
     listeners
    0.10
    读èĢħ
    0.10
    Activations Density 0.064%

    No Known Activations