© 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. 20158
    Prev
    Next
    INDEX
    Explanations

    never been

    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
    edList
    -0.11
    éĴ»çłĶ
    -0.09
     Cand
    -0.09
    æ¿®
    -0.09
    çĽį
    -0.08
    äºĨ好
    -0.08
    acts
    -0.08
    ool
    -0.08
    è¯Ĩ
    -0.08
    abil
    -0.08
    POSITIVE LOGITS
    åIJĮæĹ¶ä¹Łæĺ¯
    0.10
    æĸ°æĹ¶æľŁ
    0.09
    缸çĪ±
    0.09
    é£Łæ¬²
    0.09
    è¿Ļæĸ¹éĿ¢
    0.09
    è¿Ļ对
    0.09
    åį³ä¾¿æĺ¯
    0.09
    æľĢéĩįè¦ģ
    0.09
     каÑĩеÑģÑĤва
    0.09
    åį³ä¾¿
    0.09
    Activations Density 0.028%

    No Known Activations