© 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. 63443
    Prev
    Next
    INDEX
    Explanations

    've waited, 'd been, have been

    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
     Mile
    -0.11
    åºĸ
    -0.10
    WI
    -0.09
    shal
    -0.09
    åĦ¿
    -0.09
    ä¸ĢåĽ¢
    -0.09
    容è²Į
    -0.09
    ä¸ĩéĩĮ
    -0.09
     Abr
    -0.08
    å³
    -0.08
    POSITIVE LOGITS
     earlier
    0.13
    æĹ©çĤ¹
    0.13
    å½ĵåĪĿ
    0.12
    åı¯ä»¥æĽ´å¥½
    0.11
    æĥ³è±¡åĬĽ
    0.11
    tro
    0.10
    æıIJæĹ©
    0.10
    ä¸Ģå¼Ģå§ĭå°±
    0.09
    åĴ¬
    0.09
     Earlier
    0.09
    Activations Density 0.034%

    No Known Activations