© 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. 37138
    Prev
    Next
    INDEX
    Explanations

    bands and artists names

    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
    æķŀ
    -0.10
     Ðļи
    -0.10
    èIJ½åħ¥
    -0.10
    cntl
    -0.10
    ëĦIJ
    -0.09
    å¸ĤæķĻèĤ²
    -0.09
    å²Ľ
    -0.09
    åĦ¿å¥³
    -0.09
    ä¸įå¿į
    -0.09
     tầ
    -0.09
    POSITIVE LOGITS
    éģ£
    0.09
    说åĩºæĿ¥
    0.08
    å´®
    0.08
    æµ£
    0.08
    èĭ£
    0.08
    oni
    0.08
     proximity
    0.07
    ä½
    0.07
    éĻĦè¿ij
    0.07
     WARRANTY
    0.07
    Activations Density 0.003%

    No Known Activations