© 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. 62535
    Prev
    Next
    INDEX
    Explanations

    biographical or personal information

    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
    èģĶ缣
    -0.10
    çľĭä½ł
    -0.09
    åľ¨è¿Ļ
    -0.09
    æĭ¢
    -0.08
    план
    -0.08
    ç³Ĭæ¶Ĥ
    -0.08
    让æĪij
    -0.08
    çĻ½èıľ
    -0.08
    èµĦæ·±
    -0.08
    åħ¹
    -0.08
    POSITIVE LOGITS
    家ä¸Ń
    0.10
    æĴĴ
    0.10
    arness
    0.09
    家éĩĮ
    0.09
    bled
    0.09
     Philosophy
    0.09
    çĪ¶æ¯į
    0.09
    伤
    0.08
    ë°ķ
    0.08
    Parents
    0.08
    Activations Density 0.053%

    No Known Activations