© 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. 19354
    Prev
    Next
    INDEX
    Explanations

    Abercrombie & Fitch

    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
    æĮ¯å¥ĭ
    -0.09
    çĤ¹åĦ¿
    -0.09
     fused
    -0.09
    豸
    -0.08
    åģľ
    -0.08
     coherence
    -0.08
    èIJ¥ä¸ļ
    -0.08
    entr
    -0.08
     corrupted
    -0.08
    gue
    -0.08
    POSITIVE LOGITS
    æ¦Ķ
    0.11
    ä¸ĩæĪ·
    0.10
    ho
    0.09
    iami
    0.09
    çĶŁçĶŁ
    0.09
    çļĦçIJĨ念
    0.09
    èIJ½åı¶
    0.09
     fend
    0.08
    onne
    0.08
    åľ¨æĦı
    0.08
    Activations Density 0.002%

    No Known Activations