© 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. 52732
    Prev
    Next
    INDEX
    Explanations

    medical treatment and therapy

    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
    æĶ¶åĪ°
    -0.09
    mania
    -0.09
    åıĤè°ĭ
    -0.09
    erten
    -0.08
    reed
    -0.08
    quirer
    -0.08
    ä¹ĭ家
    -0.08
    âĭ®
    -0.08
    à¹Ĥ
    -0.08
    æľĽ
    -0.08
    POSITIVE LOGITS
    äºĪ
    0.09
    ä¸Ģ段æŶéĹ´
    0.09
    å¾ĭ
    0.09
    åįĬæľĪ
    0.08
    ä¸Ģæĸ¹éĿ¢
    0.08
    oux
    0.08
    蹬
    0.08
    ä½Ĩå¦Ĥæŀľ
    0.08
    解åĨ³éĹ®é¢ĺ
    0.08
    lyn
    0.08
    Activations Density 0.315%

    No Known Activations