© 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. 63524
    Prev
    Next
    INDEX
    Explanations

    offline applications or technology

    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
    æŀ§
    -0.09
    åıįå¤į
    -0.09
    ä¸įèĤ¯
    -0.09
    æľĢåħĪ
    -0.09
    åİĤ
    -0.09
     wspóln
    -0.09
    è°ĥ
    -0.09
    å·¥ä¸ļåĮĸ
    -0.08
    åį«çĶŁ
    -0.08
    æŀIJ
    -0.08
    POSITIVE LOGITS
    isol
    0.12
    éĹŃ
    0.11
    Offline
    0.11
    åѤç«ĭ
    0.11
     Offline
    0.10
     isolated
    0.10
    offline
    0.10
     offline
    0.10
    åѤ
    0.10
    ä¹Łèĥ½
    0.10
    Activations Density 0.106%

    No Known Activations