© 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. 39377
    Prev
    Next
    INDEX
    Explanations

    commenting on

    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
    èĩ³ä»Ĭ
    -0.12
    æѤæŶ
    -0.11
    ä¸Ģå¼Ģå§ĭå°±
    -0.11
    å±ĬæŶ
    -0.11
    edor
    -0.10
    æѤæĻĤ
    -0.10
    æľĢç»Ī
    -0.10
    å¾Īå¿«å°±
    -0.10
     ultimately
    -0.10
    æľĢåĪĿ
    -0.09
    POSITIVE LOGITS
    adays
    0.12
    纶
    0.11
    为æŃ¢
    0.10
    åĨ¶éĩij
    0.10
    åıªåī©ä¸ĭ
    0.10
    æĥ³èµ·æĿ¥
    0.10
    åıĺæĪIJäºĨ
    0.10
    aday
    0.10
    æľīäºĨ
    0.10
    åıĺæĪIJ
    0.09
    Activations Density 0.185%

    No Known Activations