© 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. 2592
    Prev
    Next
    INDEX
    Explanations

    intelligent design, information theory

    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
    éķ¿å¯¿
    -0.11
    åĢ¼å¾Ĺ
    -0.10
    è¾Ī
    -0.09
    ãĤ¹ãĥĶ
    -0.09
    èĥ¡åŃIJ
    -0.09
    åIJĥå¾Ĺ
    -0.09
    kl
    -0.09
    éĥ¨èIJ½
    -0.09
    æѦæŀĹ
    -0.09
    ãģĦãĤį
    -0.09
    POSITIVE LOGITS
    TOT
    0.10
    æīĭä¸ĭ
    0.09
    æīĭèĦļ
    0.09
    ä¸ĢæŶ
    0.09
     Totally
    0.08
    ç¥Ī
    0.08
    gorithm
    0.08
     Sz
    0.08
    леж
    0.08
     sque
    0.08
    Activations Density 0.028%

    No Known Activations