© 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. 50649
    Prev
    Next
    INDEX
    Explanations

    sweet sixteen

    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
    egen
    -0.09
    æīĩ
    -0.09
    è¢ĸ
    -0.08
    年代
    -0.08
    èĦ¸
    -0.08
     пÑĢоÑĩ
    -0.08
    å®īåħ¨æĦŁ
    -0.08
    è¿ĺæľīä»Ģä¹Ī
    -0.08
    欢
    -0.08
    绿èī²åıijå±ķ
    -0.08
    POSITIVE LOGITS
    ly
    0.11
    åѤç«ĭ
    0.10
     à¹Ĩ
    0.09
    åĵī
    0.09
    æ¹Ķ
    0.09
    æ·³
    0.09
    æĮīæŶ
    0.09
    åı¯æĢľ
    0.09
    ä¸įçŁ¥
    0.09
    quire
    0.08
    Activations Density 0.006%

    No Known Activations