© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52599
    Prev
    Next
    INDEX
    Explanations

    ticket holders, celebration, event attendees

    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
    æľīå¤ļä¹Ī
    -0.10
    çķĮçļĦ
    -0.10
    çļĦ缮åħī
    -0.09
    å¾®éĩı
    -0.09
    ëĬIJ
    -0.09
    æį
    -0.09
    幡
    -0.09
    åĩ»
    -0.09
    éļıå¤Ħ
    -0.09
    é¹Į
    -0.09
    POSITIVE LOGITS
    对å¤ĸå¼ĢæĶ¾
    0.09
    åħ¬ä¼Ĺ
    0.08
    åĢį
    0.08
    åĶ®ç¥¨
    0.08
    è°ĪæģĭçĪ±
    0.08
    人å±ħ
    0.08
    è´Ń票
    0.08
    åIJij社ä¼ļ
    0.08
    anth
    0.08
    _Enc
    0.08
    Activations Density 0.096%

    No Known Activations