© 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. 37254
    Prev
    Next
    INDEX
    Explanations

    laws and legislation

    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
    ç¼ĵ
    -0.10
    eeper
    -0.10
    顺
    -0.10
    avit
    -0.09
    éĹ»
    -0.09
    borg
    -0.08
    ä¸Ģç«Ļ
    -0.08
    èģŀ
    -0.08
    æĸ¹å¼ıè¿Ľè¡Į
    -0.08
    ä¸İæŶ
    -0.08
    POSITIVE LOGITS
    æ³ķè§Ħ
    0.12
    æ³ķå¾ĭ
    0.11
    æ³ķå¾ĭæ³ķè§Ħ
    0.10
     laws
    0.10
     regulations
    0.10
    çݯç»ķ
    0.09
     legal
    0.09
     Trot
    0.09
    ç«ĭæ³ķ
    0.09
    ha
    0.08
    Activations Density 0.079%

    No Known Activations