© 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. 7504
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and opinions

    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
    è£ħ
    -0.10
    åįłæľī
    -0.09
    ä¸īæĸ¹
    -0.09
    éĻ¬
    -0.08
    è£Ŀ
    -0.08
    çľĭä¸Ģçľĭ
    -0.08
    .Singleton
    -0.08
    串
    -0.08
    ç¦Ģ
    -0.08
    çĻ½é¢Ĩ
    -0.08
    POSITIVE LOGITS
     Jury
    0.10
    æĢ»ä½ĵ
    0.09
    éļ¾å¿ĺ
    0.09
     expectations
    0.09
    è¯Ĩ
    0.08
    èĮ§
    0.08
    æ°´ä¸Ĭ
    0.08
    å¼Ģæ°´
    0.08
    ä¸ľè·¯
    0.08
    æĦıä¹īä¸Ĭ
    0.08
    Activations Density 0.056%

    No Known Activations