© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18700
    Prev
    Next
    INDEX
    Explanations

    best to, better to

    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
    æĥ³çŁ¥éģĵ
    -0.10
    缸åħ³åĨħ容
    -0.09
    涯
    -0.09
    æī§
    -0.09
    æľ¬äºĭ
    -0.09
    责任æĦŁ
    -0.09
    æīįçŁ¥éģĵ
    -0.08
    mas
    -0.08
    èĩªå·±åĸľæ¬¢
    -0.08
     Rudd
    -0.08
    POSITIVE LOGITS
    istar
    0.10
     СегоднÑı
    0.09
    éģ¿å¼Ģ
    0.09
    ìħĢ
    0.09
     Bacon
    0.09
    Leaks
    0.09
    æµĵ缩
    0.09
    é¨İ
    0.09
    ä¸įè¦ģ太
    0.09
    CloseOperation
    0.09
    Activations Density 0.022%

    No Known Activations