© 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. 19802
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs

    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
    太å°ij
    -0.11
    æī¿åĬŀ
    -0.10
    æĺ¯ä¸Ģ款
    -0.09
    è¿ĻéĩĮæľī
    -0.09
     Animated
    -0.09
    太å¤ļçļĦ
    -0.09
    éĤ£è¾¹
    -0.09
    .Endpoint
    -0.09
    LAG
    -0.09
    lag
    -0.09
    POSITIVE LOGITS
    èµĸ以
    0.12
    æĺ¯çĶ¨æĿ¥
    0.11
    称ä¹ĭ为
    0.11
    称为
    0.10
    å¸ĮæľĽéĢļè¿ĩ
    0.09
    亲èĩª
    0.09
    çĶ¨æĿ¥
    0.09
    çĶ¨äºİ
    0.09
    æĺ¯ä¸ºäºĨ
    0.08
     blames
    0.08
    Activations Density 0.105%

    No Known Activations