© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21677
    Prev
    Next
    INDEX
    Explanations

    defendant / defendants

    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
    аÑĢи
    -0.09
    å¤ı天
    -0.08
    adium
    -0.08
     ÑģоÑģÑĤ
    -0.08
    ieres
    -0.08
    åĢį
    -0.08
    ä¹ĭç±»
    -0.08
     dashes
    -0.08
    cko
    -0.08
    åħ»çĮª
    -0.08
    POSITIVE LOGITS
    åĬ¿
    0.09
    ufs
    0.09
    енÑĤÑĢ
    0.08
    åįł
    0.08
    æĿĤ
    0.08
    eyed
    0.08
    ilih
    0.08
    åĿļæĮģä¸įæĩĪ
    0.08
    ä¸įæİĴéĻ¤
    0.08
    åij¼åĶ¤
    0.08
    Activations Density 1.616%

    No Known Activations