© 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. 47458
    Prev
    Next
    INDEX
    Explanations

    accused of / accuses of

    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
    nement
    -0.09
    åĿıäºĭ
    -0.09
     fools
    -0.09
     thuáºŃn
    -0.09
    æĿ¥åĪ°
    -0.09
    inton
    -0.08
    è¸Į
    -0.08
    社ä¼ļ稳å®ļ
    -0.08
    èĢĮæĿ¥
    -0.08
    çļĦæĦ¿æľĽ
    -0.08
    POSITIVE LOGITS
    å«Įçĸij
    0.17
    æ¶īå«Į
    0.16
     accused
    0.14
    æĮĩæݧ
    0.13
    æĢĢçĸij
    0.13
     suspicion
    0.13
    çĸijä¼¼
    0.13
     suspect
    0.12
    æĮĩè´£
    0.12
     accuses
    0.12
    Activations Density 0.107%

    No Known Activations