© 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. 18960
    Prev
    Next
    INDEX
    Explanations

    after 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
    åıĬåħ¶
    -0.09
    以åıĬåħ¶ä»ĸ
    -0.08
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
    ograms
    -0.08
    IPA
    -0.08
    ype
    -0.08
    ãģ¨ãĤĤ
    -0.08
    Ñĩа
    -0.08
    _FIFO
    -0.07
     Pur
    -0.07
    POSITIVE LOGITS
    eras
    0.10
    è¿Ļ家ä¼Ļ
    0.09
    åĴĮæĬĢæľ¯
    0.09
    edin
    0.09
     trÃł
    0.09
    ä½ĵèĤ²é¦Ĩ
    0.09
    åĢĻéĢī
    0.09
    å¿ĥçIJĨåĴ¨è¯¢
    0.08
    åĴĮ个人
    0.08
    ä»Ģä¹Īåı«
    0.08
    Activations Density 0.725%

    No Known Activations