© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63816
    Prev
    Next
    INDEX
    Explanations

    purchased or bought

    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¸Ģ个个
    -0.10
    ä¸Ģ次次
    -0.10
    ä¸Ģè½®
    -0.09
    é»ijçĻ½
    -0.09
    çĵ¦
    -0.09
    ä¾Ľæ±Ĥ
    -0.09
    ä¸Ģå¹ķ
    -0.08
    oth
    -0.08
    urred
    -0.08
    ä¸ĵåĪ©
    -0.08
    POSITIVE LOGITS
    ä¹°åĪ°
    0.17
     purchased
    0.16
    è´Ńä¹°
    0.15
    ä¹°äºĨ
    0.14
    ä¹°çļĦ
    0.13
    è²·ãģ£ãģŁ
    0.13
     purchase
    0.13
     bought
    0.11
     purchases
    0.11
    purchase
    0.11
    Activations Density 0.138%

    No Known Activations