© 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. 8078
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    _streams
    -0.10
     wÅĽ
    -0.09
    ä»İæľª
    -0.09
    ãĥ¬ãĤ¹ãĥĪ
    -0.09
    äºĨä¸Ģåı£
    -0.09
    åī©
    -0.09
    _hresult
    -0.09
    /tos
    -0.09
    lover
    -0.09
    TRGL
    -0.09
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.14
     or
    0.14
    ä¹ĭç±»çļĦ
    0.11
    åıĬ以ä¸Ĭ
    0.11
    æĪĸèĢħåħ¶ä»ĸ
    0.10
    ä¹ĥèĩ³
    0.10
    æĪĸå¤ļæĪĸå°ij
    0.10
    æĪĸåħ¶ä»ĸ
    0.09
     تÙĤ
    0.09
    大æ¦Ĥ
    0.09
    Activations Density 0.523%

    No Known Activations