© 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. 18581
    Prev
    Next
    INDEX
    Explanations

    provide you with

    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¸
    -0.10
    åĮĨåĮĨ
    -0.09
    æ±ĤåĬ©
    -0.09
    产ä¸ļéĽĨèģļ
    -0.09
    ä¸įçŁ¥ä¸įè§ī
    -0.09
    ight
    -0.09
    åģļä¸Ģ个
    -0.09
    ifying
    -0.09
    arent
    -0.09
    atoria
    -0.09
    POSITIVE LOGITS
    å¿ħè¦ģçļĦ
    0.09
    è¶³å¤ŁçļĦ
    0.08
    ç´§å¼ł
    0.08
     thêm
    0.08
    tasks
    0.08
    ä¸ĢäºĮ
    0.08
    æĸ¹åIJij
    0.08
    åĻİ
    0.08
    æĪĺçķ¥
    0.08
    æīĢéľĢè¦ģçļĦ
    0.07
    Activations Density 0.069%

    No Known Activations