© 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. 20375
    Prev
    Next
    INDEX
    Explanations

    companies or organizations

    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
    ä»ĸçļĦ
    -0.11
    ä»ĸåľ¨
    -0.10
     ÑģамоÑģÑĤоÑı
    -0.10
    ä»ĸæĺ¯
    -0.10
    åĸľæ¬¢åIJĥ
    -0.10
    å³Ń
    -0.10
    SOLE
    -0.09
    ä»ĸèĩªå·±
    -0.09
    obe
    -0.09
    ä»ĸä¹Ł
    -0.09
    POSITIVE LOGITS
    ’s
    0.11
    ฯ
    0.11
    åıĬåħ¶
    0.10
    's
    0.10
    æIJŀ
    0.09
     employees
    0.09
    åİŁåħĪ
    0.09
    åīį身
    0.09
    åijĺå·¥
    0.09
    åĪĽå§ĭ人
    0.09
    Activations Density 0.049%

    No Known Activations