© 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. 18980
    Prev
    Next
    INDEX
    Explanations

    the + noun phrase

    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
    æīĢè°ĵçļĦ
    -0.09
    éĤ£ä»½
    -0.08
     اÙĦÙħÙĤ
    -0.08
    smarty
    -0.08
    ä¼ģä¸ļçļĦ
    -0.08
    è¦ģæĺ¯
    -0.08
    è¿Ļ份
    -0.08
    ä¸Ģæł·çļĦ
    -0.08
     söz
    -0.08
    RGBA
    -0.08
    POSITIVE LOGITS
    ç¾İæĻ¯
    0.10
    orate
    0.09
    å·®åĪ«
    0.09
    åı°éĺ¶
    0.09
     ÑįкÑģ
    0.08
    Æ°Æ¡i
    0.08
    æŀĦ
    0.08
    å·®å¼ĤåĮĸ
    0.08
    å¢Ļ
    0.08
    çģ¾
    0.08
    Activations Density 0.021%

    No Known Activations