© 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. 36689
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

    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
    æĺ¯æ²¡æľī
    -0.10
    ç°ª
    -0.09
    è¿ĻèĪ¬
    -0.09
    å®ŀåľ¨æĺ¯å¤ª
    -0.09
    æĪijå¾Ī
    -0.09
    åĪ·åį¡
    -0.09
    åľ¨è¿Ļ
    -0.09
    InThe
    -0.09
    éĥ½æ²¡æľī
    -0.08
    æł¹æľ¬å°±ä¸į
    -0.08
    POSITIVE LOGITS
     McKenzie
    0.08
    argas
    0.08
     ability
    0.08
    河水
    0.07
    av
    0.07
    çĶŁæľº
    0.07
     Heller
    0.07
    æ½ľåĬĽ
    0.07
     closest
    0.07
    ski
    0.07
    Activations Density 0.166%

    No Known Activations