© 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. 57213
    Prev
    Next
    INDEX
    Explanations

    and / sowie / and others

    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
    æĪĸå¤ļ
    -0.12
    åĴĮå®ĮåĸĦ
    -0.11
    imd
    -0.10
     Richards
    -0.10
    .hr
    -0.09
    tá
    -0.09
    èħ¾é£ŀ
    -0.09
    æĭ¬
    -0.09
    ä¸İåıijå±ķ
    -0.09
    éļĺ
    -0.09
    POSITIVE LOGITS
    以åıĬåħ¶ä»ĸ
    0.17
    以åıĬ
    0.16
     serta
    0.12
     sowie
    0.12
    ãģĿãģĹãģ¦
    0.12
     ê·¸ë¦¬ê³ł
    0.12
     alike
    0.12
    è¿Ļ两个
    0.09
    çĶļèĩ³æĺ¯
    0.09
     respectively
    0.09
    Activations Density 0.396%

    No Known Activations