© 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. 62594
    Prev
    Next
    INDEX
    Explanations

    give me your

    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
    ä¹ĭä¸ĭ
    -0.09
    ç»ķ
    -0.09
    çļĦéĩįçĤ¹
    -0.08
     Dept
    -0.08
    人士
    -0.08
    å³Ļ
    -0.08
    æ¡´
    -0.08
    天çĶŁ
    -0.08
    izioni
    -0.08
    æĪij说
    -0.08
    POSITIVE LOGITS
    æľĢå¿«
    0.09
     ENUM
    0.09
    ä»°
    0.09
    庶
    0.09
    å±ł
    0.09
    äºĨä¸Ģ份
    0.09
    SELL
    0.09
    äºĨä¸Ģ
    0.08
    äºĮ人
    0.08
     Www
    0.08
    Activations Density 0.025%

    No Known Activations