© 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. 54288
    Prev
    Next
    INDEX
    Explanations

    bankruptcy and creditors

    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
    éĺ³åħī
    -0.11
    æĻķ
    -0.10
    éŀŃ
    -0.10
    dispatch
    -0.09
    FORE
    -0.09
     Jeb
    -0.08
    çĻ½æ²Ļ
    -0.08
    ä½ĺ
    -0.08
    æ°¸ä¹ħ
    -0.08
    ä¹Łæĺ¯å¦ĤæѤ
    -0.08
    POSITIVE LOGITS
    åĢºæĿĥ人
    0.12
    ä¼ĺåħĪ
    0.10
    éĩįæķ´
    0.09
    å¤įèĭı
    0.09
    éĢĥçĶŁ
    0.09
    деж
    0.09
    æĬķéĻį
    0.09
    ç«ŀ
    0.09
     Disposable
    0.09
    çł´äº§
    0.08
    Activations Density 0.165%

    No Known Activations