© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49176
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    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
    acha
    -0.09
    anne
    -0.09
    æºIJæºIJä¸įæĸŃ
    -0.09
    ä½Ĩå®ĥ
    -0.09
    oren
    -0.09
    ä¸įä»ħå¦ĤæѤ
    -0.08
    ä½Ĩä¹Ł
    -0.08
    é«Ģ
    -0.08
    主è¦ģåİŁåĽł
    -0.08
    EV
    -0.08
    POSITIVE LOGITS
    æľīçļĦ人
    0.14
    æľīçļĦ
    0.13
    æ¯Ķå¦Ĥ
    0.11
    ä¾ĭãģĪãģ°
    0.11
    å¦Ĥæŀľæĺ¯
    0.11
    æľīäºĽ
    0.10
    æĺ¯åIJ¦ä¼ļ
    0.10
    ä¾ĭå¦Ĥ
    0.10
    åIJĦæľī
    0.10
    åĴĮåľ°åĮº
    0.09
    Activations Density 0.169%

    No Known Activations