© 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. 31483
    Prev
    Next
    INDEX
    Explanations

    pandas data manipulation

    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
    è¿Ļ个èģĮä¸ļ
    -0.10
    èħ¾é£ŀ
    -0.10
    ä¸Ģåī¯
    -0.10
    åħ¨èº«
    -0.09
    è¿ĩå¾Ģ
    -0.09
    жал
    -0.09
    å¤ĸåĩº
    -0.09
    äºĶåįĥ
    -0.09
    ç§ijæķĻ
    -0.09
    使人
    -0.08
    POSITIVE LOGITS
    çĭ¬è§Ĵ
    0.09
     pandas
    0.09
     Series
    0.08
    å½ĺ
    0.08
    ç²ĺ
    0.08
     na
    0.08
    Series
    0.08
    Surv
    0.08
     Pand
    0.08
     '`
    0.08
    Activations Density 0.366%

    No Known Activations