© 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. 723
    Prev
    Next
    INDEX
    Explanations

    faith in the show

    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
    串
    -0.10
     иÑģÑĤоÑĢиÑı
    -0.09
    igure
    -0.08
    .fun
    -0.08
    æĪijçİ°åľ¨
    -0.08
    对æĪij
    -0.08
    åİĭåĬĽ
    -0.08
    utta
    -0.08
     ado
    -0.08
    peat
    -0.08
    POSITIVE LOGITS
    çļĦçľ¼åħī
    0.11
    ä¸įçĽ¸ä¿¡
    0.10
    ä½ĵ系建设
    0.10
    æľīèĥ½åĬĽ
    0.10
    ä¸Ģå®ļèĥ½
    0.09
    çĽ²
    0.09
     capabilities
    0.09
    èĥ½åĬĽåĴĮ
    0.09
    ä¿¡ä»°
    0.09
    eneg
    0.09
    Activations Density 0.032%

    No Known Activations