© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18846
    Prev
    Next
    INDEX
    Explanations

    second-hand selling

    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
    åŁĭ
    -0.10
    èĪŀ
    -0.10
    born
    -0.09
    åIJĵ
    -0.09
    主æŨ
    -0.08
     bÃłn
    -0.08
    eken
    -0.08
    urst
    -0.08
    igh
    -0.08
    _binding
    -0.08
    POSITIVE LOGITS
    able
    0.12
    èIJ¥åħ»ä»·åĢ¼
    0.10
    åĴĮå¹³
    0.09
    ãģĦãģªãģĦ
    0.09
    èµ·æĿ¥
    0.09
    åĸĤ
    0.09
    èĩ¬
    0.09
    çĭ¬ä¸Ģ
    0.08
    ABLE
    0.08
    ree
    0.08
    Activations Density 0.006%

    No Known Activations