© 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. 38106
    Prev
    Next
    INDEX
    Explanations

    then followed by an action

    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
     пÑĢедÑģÑĤавлÑı
    -0.09
    æĪ¾
    -0.09
    讵
    -0.09
    ãģ¾ãģĹãģ¦
    -0.09
     giÃł
    -0.08
     Norris
    -0.08
    åIJĮçŃī
    -0.08
    åĩĮæĻ¨
    -0.08
    ä¸Ģå¼Ģå§ĭå°±
    -0.08
    æ´»è·ĥ
    -0.08
    POSITIVE LOGITS
     then
    0.17
    çĦ¶åIJİåĨį
    0.17
    çĦ¶åIJİ
    0.17
    åIJİåĨį
    0.15
     заÑĤем
    0.15
    then
    0.14
    éļıåIJİ
    0.13
    Then
    0.13
     Then
    0.13
    çĦ¶å¾Į
    0.13
    Activations Density 0.636%

    No Known Activations