© 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. 61299
    Prev
    Next
    INDEX
    Explanations

    cup of tea

    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¸Ģæľµ
    -0.14
    ä¸ĢæĬ¹
    -0.11
    ä¸Ģèīĺ
    -0.11
    çļĦä¸Ģ款
    -0.10
    ä¸Ģå¹ħ
    -0.10
    ä¸Ģé¢Ĺ
    -0.10
    ä¸Ģ份
    -0.10
    ä¸Ģæŀ¶
    -0.10
    ä¸Ģ座
    -0.10
    äºĨä¸Ģ份
    -0.10
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.17
    åİļåİļçļĦ
    0.11
    è¿ĩåIJİ
    0.09
    åĩĿ
    0.09
    çľĭä¼¼
    0.08
    sing
    0.08
    ç²¾
    0.08
    ãģ¾ãģ¾
    0.08
    quals
    0.08
    è´¯éĢļ
    0.08
    Activations Density 0.066%

    No Known Activations