© 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. 12131
    Prev
    Next
    INDEX
    Explanations

    nature has

    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
    æĬľãģij
    -0.10
    çĵĴ
    -0.10
    ä¸ĥæĺŁ
    -0.09
    ãģĤãģª
    -0.09
    ä¸ĭåİ»
    -0.09
    çļĦçĶŁåij½
    -0.09
    æľŁåĨħ
    -0.08
     Hung
    -0.08
    çĺĹ
    -0.08
    ä¹ĭ称
    -0.08
    POSITIVE LOGITS
    æĥ©ç½ļ
    0.10
    é¦Ī
    0.10
    ç»ĻæĪij们
    0.09
    èĨĤ
    0.09
     пÑĥнк
    0.08
    åħ¬å¹³
    0.08
    punk
    0.08
    å°¤åħ¶æĺ¯åľ¨
    0.08
    æ®ĭéħ·
    0.08
    road
    0.08
    Activations Density 0.052%

    No Known Activations