© 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. 37721
    Prev
    Next
    INDEX
    Explanations

    give it a go

    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
    Ùħات
    -0.09
     grav
    -0.09
    嶷
    -0.09
    çijĹ
    -0.08
    çĶ¾
    -0.08
    oop
    -0.08
    fy
    -0.08
    å¦Ļ
    -0.08
    нÑİ
    -0.08
    å©¿
    -0.08
    POSITIVE LOGITS
    è¾Ħ
    0.10
    çĺª
    0.09
    åIJİå¤ĩ
    0.09
    åľ¨éĩĮéĿ¢
    0.08
    æľºä¼ļ
    0.08
    å»ĵ
    0.08
    究
    0.08
    å¼Ĥåľ°
    0.08
    追æ±Ĥ
    0.08
    çļĸ
    0.08
    Activations Density 0.012%

    No Known Activations