© 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. 7912
    Prev
    Next
    INDEX
    Explanations

    section devoted 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
    aurus
    -0.08
     Suk
    -0.08
    åı£ä¸Ń
    -0.08
    æīĭä¸Ń
    -0.08
     Sylv
    -0.08
    onis
    -0.08
    çīµ
    -0.08
    éĩįåĽŀ
    -0.08
    é¼ł
    -0.08
     aff
    -0.08
    POSITIVE LOGITS
    ä¸ĵéŨ
    0.22
     dedicated
    0.15
     devoted
    0.14
    å°±æѤ
    0.13
    为æѤ
    0.13
    ä¸ĵéĹ¨ä¸º
    0.13
    å°Ī
    0.12
    ä¸ĵ
    0.12
    ä¸ĵ项
    0.12
     dedicate
    0.11
    Activations Density 0.124%

    No Known Activations