© 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. 50748
    Prev
    Next
    INDEX
    Explanations

    (hereinafter referred to)

    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
    éľı
    -0.09
    çıįæĥľ
    -0.08
    PCM
    -0.08
    ä»Ĺ
    -0.08
    nable
    -0.08
    æłĩæĺİ
    -0.08
    å¼Ľ
    -0.08
    ÑģÑĤв
    -0.07
    æĶ¯æŀ¶
    -0.07
    鼷æĸ¯
    -0.07
    POSITIVE LOGITS
    以ä¸ĭç®Ģ称
    0.16
    ä¸ĭ称
    0.11
    ç®Ģ称
    0.11
     throughout
    0.11
    身å¤Ħ
    0.10
    abr
    0.10
    æĬ¥åIJį
    0.10
     referred
    0.10
     here
    0.10
    æĸ¹ä¾¿
    0.10
    Activations Density 0.213%

    No Known Activations