© 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. 52275
    Prev
    Next
    INDEX
    Explanations

    conviction or convicted

    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
    讹
    -0.10
    ãĤ¯ãĥ©ãĥĸ
    -0.10
    OTA
    -0.10
    otron
    -0.09
    çĥŃéĶĢ
    -0.09
    ograms
    -0.09
    holm
    -0.09
    åĬłçıŃ
    -0.09
    Leaks
    -0.08
    papers
    -0.08
    POSITIVE LOGITS
    ç½ļ
    0.10
    å¤Ħç½ļ
    0.10
    楼ä¸ĭ
    0.10
     convictions
    0.09
    _conv
    0.09
     conviction
    0.09
    累累
    0.09
    å¾ĹæĦı
    0.09
     penalties
    0.08
    SizeMode
    0.08
    Activations Density 0.199%

    No Known Activations