© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47549
    Prev
    Next
    INDEX
    Explanations

    know the

    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
    Negative Logits
    дей
    -0.11
    æĪijåıijçİ°
    -0.09
    è·¨
    -0.09
    åijĬè¯īæĪij们
    -0.09
    æĪijçĽ¸ä¿¡
    -0.09
    æ´ĩ
    -0.09
    èĥ½çľĭåĩº
    -0.09
    éĨĴ
    -0.09
    ä¸įç¡®å®ļæĢ§
    -0.08
    EMU
    -0.08
    POSITIVE LOGITS
    ledge
    0.09
    å½ĵä»ĸ
    0.08
    æĪ¿ä¸ľ
    0.08
    ä»ĺ
    0.08
    Pay
    0.08
    bound
    0.08
    æĥħåĨµ
    0.08
    åij½
    0.08
    è¦ģåİ»
    0.08
    off
    0.08
    Activations Density 0.027%

    No Known Activations