© 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. 2724
    Prev
    Next
    INDEX
    Explanations

    provided + preposition

    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
    紧迫
    -0.10
    æĴ¼
    -0.09
    _Param
    -0.09
    åĽłåľ°
    -0.09
    erry
    -0.09
    pga
    -0.08
    åijĽ
    -0.08
    aked
    -0.08
    åij¦
    -0.08
    amed
    -0.08
    POSITIVE LOGITS
    chy
    0.09
    ../../../
    0.09
    zial
    0.08
    çļĦæŶéĹ´éĩĮ
    0.08
     incontro
    0.08
    osis
    0.08
    RU
    0.08
    çļĦæĹ¥åŃIJéĩĮ
    0.08
    ä¼Ļ
    0.08
    身边çļĦ
    0.08
    Activations Density 0.047%

    No Known Activations