© 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. 9503
    Prev
    Next
    INDEX
    Explanations

    credit rating agencies and boards

    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
    äºī
    -0.09
    jec
    -0.08
    æ´»
    -0.08
    bau
    -0.08
    stead
    -0.08
    Translator
    -0.08
    åıĭ好
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    åĶ®
    -0.08
    éĽķåĪ»
    -0.08
    POSITIVE LOGITS
     marks
    0.09
    çĪ·
    0.09
    iggins
    0.09
    对ä¼ģä¸ļ
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.08
    å¹½
    0.08
    ä¸ĬéŨ
    0.08
    严èĤĥ
    0.08
    ç§ģèIJ¥
    0.08
    è§ĦåĪĻ
    0.08
    Activations Density 0.074%

    No Known Activations