© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37048
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è¿ĩåĪĨ
    -0.10
    udi
    -0.10
    layan
    -0.10
    åı¬åĶ¤
    -0.10
    alic
    -0.09
    otland
    -0.09
    åı·åı¬
    -0.09
    æīĵä»Ĺ
    -0.09
    ä¸ŃåĽ½æ¢¦
    -0.09
    éĻIJ度
    -0.09
    POSITIVE LOGITS
    2
    0.08
    oc
    0.08
    æĭĹ
    0.08
    å®ģ
    0.08
     Robertson
    0.08
    9
    0.08
    å¹´ä¹ĭ
    0.08
    ä½³
    0.08
     Ist
    0.08
    1
    0.08
    Activations Density 0.000%

    No Known Activations