© 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. 19162
    Prev
    Next
    INDEX
    Explanations

    describing style or characteristics

    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
    omal
    -0.09
    nis
    -0.08
    ä¹ĭ声
    -0.08
     гаÑĢан
    -0.08
    Å¡e
    -0.08
    omap
    -0.08
     ÙħÙĤ
    -0.08
    nm
    -0.08
    èĭĩ
    -0.08
     Rah
    -0.08
    POSITIVE LOGITS
    ä¸ī家
    0.12
    å°±å¦ĤåIJĮ
    0.10
    ä¸Ĭåīį
    0.10
    åĴĮæĬĢæľ¯
    0.10
    å¸ģ
    0.10
    第äºĮæī¹
    0.09
    ä¸Ĭæľī
    0.09
    å·į
    0.09
    å¾Īå¤ļæľĭåıĭ
    0.09
    è¿ĻäºĽäºº
    0.09
    Activations Density 0.132%

    No Known Activations