© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37100
    Prev
    Next
    INDEX
    Explanations

    set up, purchase, provide, feed, keep, find

    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
    æĭĶ
    -0.09
     Commons
    -0.09
    esses
    -0.08
     Bowman
    -0.08
    è¾¾ä¸įåĪ°
    -0.08
    æĬ¥éĢģ
    -0.08
    =edge
    -0.08
    ervice
    -0.08
    çĶŁçĶŁ
    -0.07
    çijĽ
    -0.07
    POSITIVE LOGITS
    åĩĨå¤ĩå·¥ä½ľ
    0.14
    é¦ĸåħĪè¦ģ
    0.13
    åĩĨå¤ĩ好
    0.11
    ç¡®å®ļ
    0.11
    çŁ¥éģĵèĩªå·±
    0.11
    åĨ³å®ļ
    0.11
    åĨ³å®ļäºĨ
    0.11
    è¦ģèĢĥèĻij
    0.11
    éĢĤåIJĪèĩªå·±
    0.10
    é¦ĸåħĪæĺ¯
    0.10
    Activations Density 0.088%

    No Known Activations