© 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. 8328
    Prev
    Next
    INDEX
    Explanations

    forgetting or remembering

    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
    èĪįå¾Ĺ
    -0.10
    ä¸įåı¯æĢĿè®®
    -0.09
    пÑĢавлÑı
    -0.09
    è¶ģçĿĢ
    -0.09
    ä¸įçķĻ
    -0.08
    è¶ģ
    -0.08
     enclosure
    -0.08
    opi
    -0.08
    ray
    -0.08
    ä¸įåı¯æĢĿ
    -0.08
    POSITIVE LOGITS
     تÙħاÙħا
    0.10
    åĪĿè¡·
    0.10
     altogether
    0.09
    çİ°æľīçļĦ
    0.09
    è°Ľ
    0.08
    以èĩ³äºİ
    0.08
     вообÑīе
    0.08
    寡
    0.08
    èĤ¡
    0.08
     bis
    0.08
    Activations Density 0.012%

    No Known Activations