© 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. 16893
    Prev
    Next
    INDEX
    Explanations

    is, punctuation

    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
     Mason
    -0.08
     Sons
    -0.08
    çŃł
    -0.08
    éªĬ
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    ä¸į便
    -0.08
    ãģªãģĮãĤī
    -0.08
     оÑĤз
    -0.07
     Chronicles
    -0.07
     бил
    -0.07
    POSITIVE LOGITS
    ç®Ģ称
    0.14
    åĪº
    0.10
    æļ¨
    0.09
    è¿Ļåı¥è¯Ŀ
    0.09
    Defaults
    0.09
    浸泡
    0.09
    æīĵæĬĺ
    0.09
    оÑĤ
    0.08
    èIJ½åĪ°å®ŀå¤Ħ
    0.08
    åij¼
    0.08
    Activations Density 0.371%

    No Known Activations