© 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. 6802
    Prev
    Next
    INDEX
    Explanations

    disasters at sea

    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
    ecer
    -0.09
    两端
    -0.09
    æ¹ĺ
    -0.09
    _demand
    -0.09
    æŸ
    -0.08
    ç°ª
    -0.08
    _POOL
    -0.08
    æĮĸæİĺ
    -0.08
    æľ«
    -0.08
    ä¸ĬçıŃ
    -0.08
    POSITIVE LOGITS
    åģľä¸ĭ
    0.12
    èĪªçº¿
    0.11
    驶
    0.11
    èĪªéģĵ
    0.10
    èĪ±
    0.10
    åģı离
    0.10
    æµ·åŁŁ
    0.10
    çĩĥæ²¹
    0.10
    èĪ¹èĪ¶
    0.09
    åģľä¸ĭæĿ¥
    0.09
    Activations Density 0.061%

    No Known Activations