© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36634
    Prev
    Next
    INDEX
    Explanations

    bankruptcy and bankruptcies

    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
    饵
    -0.09
    arf
    -0.09
    èĤ²
    -0.08
    çıł
    -0.08
    é¹
    -0.08
    平淡
    -0.08
    éĢĤ
    -0.08
    ä¸Ģä½ĵ
    -0.08
    èĭ¹
    -0.08
    HEN
    -0.08
    POSITIVE LOGITS
    çł´äº§
    0.21
    åĢĴéĹŃ
    0.16
     bankruptcy
    0.14
     bankrupt
    0.14
    å¡Į
    0.12
    çģŃ亡
    0.11
    å´©æºĥ
    0.10
    æ¿Ĵ临
    0.10
    æĸ°éĻĪ代谢
    0.10
    宣åijĬ
    0.10
    Activations Density 0.100%

    No Known Activations