© 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. 52593
    Prev
    Next
    INDEX
    Explanations

    shall receive or be

    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
    ä¼IJ
    -0.09
    åĴĮ个人
    -0.08
    åĽ´
    -0.08
    æİı
    -0.08
    åĿĹ
    -0.08
    çİ®
    -0.08
     olmadıģı
    -0.08
    ilst
    -0.08
    pany
    -0.08
    çĨŁçŁ¥
    -0.08
    POSITIVE LOGITS
    享åıĹ
    0.12
    åħį
    0.10
    社ä¼ļæķĪçĽĬ
    0.10
    çĦķ
    0.10
    æĦīæĤ¦
    0.09
    享çĶ¨
    0.09
     гаÑĢан
    0.09
    åľ¨æľªæĿ¥
    0.09
    åħ¶æīĢ
    0.09
    è§IJ
    0.09
    Activations Density 0.033%

    No Known Activations