© 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. 1274
    Prev
    Next
    INDEX
    Explanations

    possessive and 'is'/'was' followed by words

    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
    çļĦçľ¼ç¥ŀ
    -0.10
    鸳
    -0.10
    _san
    -0.09
    èħ¹
    -0.09
    åĺŁ
    -0.09
    eus
    -0.09
    æł¹æľ¬å°±ä¸į
    -0.09
     Dexter
    -0.08
    Returned
    -0.08
    ç³Ĭ
    -0.08
    POSITIVE LOGITS
    LTR
    0.10
    çģı
    0.10
    æ½ĩæ´Ĵ
    0.09
     важно
    0.08
    nap
    0.08
     ê·ľìłķ
    0.08
    奴
    0.08
    å½ĵå±Ģ
    0.08
     ме
    0.08
    æĺ¯æĪijçļĦ
    0.08
    Activations Density 0.063%

    No Known Activations