© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64072
    Prev
    Next
    INDEX
    Explanations

    credibility and believability

    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
    Negative Logits
    OwnerId
    -0.10
     деÑıÑĤелÑĮ
    -0.09
     suit
    -0.09
     влад
    -0.09
    å¼ĢæĪ·
    -0.09
    å¯ĨåĪĩ
    -0.09
     Swords
    -0.09
     Ade
    -0.09
    é¦Ķ
    -0.08
    æ¹
    -0.08
    POSITIVE LOGITS
     credibility
    0.25
    åı¯ä¿¡
    0.24
    æĿĥå¨ģ
    0.20
    ä¿¡èªī
    0.18
     credible
    0.17
    è¯ļä¿¡
    0.17
    cred
    0.15
    ä¿¡ä»»
    0.15
    ä¿¡èµĸ
    0.15
    çļĦä¿¡ä»»
    0.14
    Activations Density 0.080%

    No Known Activations