© 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. 56444
    Prev
    Next
    INDEX
    Explanations

    "that's right" or "yes"

    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
    å²ģæŶ
    -0.10
    èĬ±çĵ£
    -0.09
    ichel
    -0.09
     Zum
    -0.09
    etable
    -0.09
    à¹ģà¸Ĥ
    -0.09
    ettel
    -0.09
     HÆ°Æ¡ng
    -0.09
    oran
    -0.08
     ÑģооÑĤвеÑĤ
    -0.08
    POSITIVE LOGITS
    åŃĹåı·
    0.11
     именно
    0.10
    å°±è¿Ļæł·
    0.09
    å®ŀå®ŀåľ¨åľ¨
    0.09
    å°±è¿Ļä¹Ī
    0.09
     Devin
    0.08
    è¿Ļæł·ä¸Ģ个
    0.08
    å®ĥåı¯ä»¥
    0.08
    以éĺ²
    0.08
    çĶ¨æ°´
    0.08
    Activations Density 0.039%

    No Known Activations