© 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. 57521
    Prev
    Next
    INDEX
    Explanations

    proponents or advocates

    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
    ä¹IJè§Ĥ
    -0.09
    æĸ°ä¸ī
    -0.09
    宽æĿ¾
    -0.09
    交éĢļè¿IJè¾ĵ
    -0.09
    è¾
    -0.09
    人身
    -0.08
    _eg
    -0.08
    寮
    -0.08
    åIJĮå¿ĥ
    -0.08
    Shares
    -0.08
    POSITIVE LOGITS
    æĬµåĪ¶
    0.16
    éĺ»æĮ¡
    0.14
    åıį对
    0.14
    éĺ»æŃ¢
    0.13
    æĭĴç»Ŀ
    0.13
    æĮijåīĶ
    0.12
    è´¨çĸij
    0.12
    åıįæĦŁ
    0.11
    éĺ»ç¢į
    0.11
    å«ī
    0.11
    Activations Density 0.297%

    No Known Activations