© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7675
    Prev
    Next
    INDEX
    Explanations

    increase or decrease from previous

    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
    Negative Logits
    纸ä¸Ĭ
    -0.09
    LOY
    -0.09
    欢è¿İæĤ¨
    -0.09
    _TA
    -0.09
    ç¼¥
    -0.09
    RI
    -0.09
    ав
    -0.08
    âĹĪ
    -0.08
    ä½ŀ
    -0.08
    cov
    -0.08
    POSITIVE LOGITS
     previously
    0.11
     previous
    0.10
    å½ĵæĹ¥
    0.10
    举äºļ
    0.09
     ÑĢанее
    0.09
    ä¹ĭåīį
    0.09
     Previously
    0.09
    åħĪåīį
    0.09
    Previously
    0.09
    åĩĢèµĦ产
    0.08
    Activations Density 0.014%

    No Known Activations