© 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. 62968
    Prev
    Next
    INDEX
    Explanations

    working with

    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
    ç§ijæĬĢåĽŃ
    -0.12
    åĬŁè¯¾
    -0.10
    åĨ³
    -0.09
    羸
    -0.09
    аÑİÑĤÑģÑı
    -0.09
    ä¸Ĭå¸Ĥ
    -0.09
    ç¨Ķ
    -0.09
    å·¥ä½ľä¼ļè®®
    -0.09
    奴éļ¶
    -0.09
    çıī
    -0.09
    POSITIVE LOGITS
     дÑĥÑħ
    0.09
    ä½Ļ
    0.08
    åIJĦåľ°
    0.08
    -sama
    0.08
    igel
    0.08
     people
    0.08
    ëĬĺ
    0.07
    æĤ¨
    0.07
    à¹Ĥร
    0.07
     dam
    0.07
    Activations Density 0.024%

    No Known Activations