© 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. 38125
    Prev
    Next
    INDEX
    Explanations

    settlement or colony

    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
    æŀ¯
    -0.09
    æİ¥å¾ħ
    -0.09
    åĬŀ好
    -0.09
    bnb
    -0.09
    	UN
    -0.08
    éĺ¶
    -0.08
    åįĩ
    -0.08
    ');?>
    -0.08
    ASM
    -0.08
    éļİ
    -0.08
    POSITIVE LOGITS
    rub
    0.12
    å®īç½®
    0.11
    å®ļå±ħ
    0.10
    èĮĹ
    0.10
    ç±³é¥Ń
    0.09
     rub
    0.09
    æ¥Ķ
    0.09
    åģ¥
    0.09
    Rub
    0.09
    Ø´Ùħ
    0.09
    Activations Density 0.102%

    No Known Activations