© 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. 8055
    Prev
    Next
    INDEX
    Explanations

    luxury car brands

    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
    ä¼ijåģĩ
    -0.09
    æ´»åĬĽ
    -0.09
    岬
    -0.09
     SetProperty
    -0.09
    lete
    -0.08
    æĸ¤
    -0.08
    flux
    -0.08
     Jur
    -0.08
    äºĨä¸Ģåı£
    -0.08
    antry
    -0.08
    POSITIVE LOGITS
    oft
    0.09
    æĭ¾
    0.08
    åħ¸ç¤¼
    0.08
    客æĪ·æľįåĬ¡
    0.08
    _dicts
    0.08
    éĢ¸
    0.08
     freder
    0.08
    æ·ij
    0.08
     GOLD
    0.08
    ìł¤
    0.08
    Activations Density 0.014%

    No Known Activations