© 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. 7588
    Prev
    Next
    INDEX
    Explanations

    preface and dedication

    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
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.10
    _prov
    -0.09
    çħŀ
    -0.09
    пÑĥÑĤ
    -0.08
    å¼Ģæľº
    -0.08
    ãĥ¥ãĥ¼
    -0.08
    ëĭ¹
    -0.08
    åıī
    -0.08
    èľ»
    -0.08
    ä¸Ģä¸ĩ
    -0.08
    POSITIVE LOGITS
    PEAR
    0.10
    æ£Ģå¯Ł
    0.09
    asis
    0.09
    åľ¨æĪijçļĦ
    0.09
    éĩįçĤ¹é¢ĨåŁŁ
    0.09
    èįı
    0.08
    äººæł¼
    0.08
    redits
    0.08
    visor
    0.08
    æī§æĦı
    0.08
    Activations Density 0.007%

    No Known Activations