© 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. 810
    Prev
    Next
    INDEX
    Explanations

    fear and worry

    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
    æijĬ
    -0.10
    è¡į
    -0.10
    污泥
    -0.10
    ç¾ŀ
    -0.10
     пеÑĩ
    -0.09
    ä¹ĭ乡
    -0.09
    _STACK
    -0.09
    çĻ£
    -0.09
     Overse
    -0.09
    à¸Ĭà¸Ńà¸ļ
    -0.09
    POSITIVE LOGITS
    æĭħå¿ĥ
    0.17
    æĵĶå¿ĥ
    0.14
    以为
    0.14
    è¿ĺ以为
    0.13
    æĭħ忧
    0.13
    害æĢķ
    0.12
    æĭħ
    0.12
    以çĤº
    0.12
    æĢķ
    0.11
     worry
    0.11
    Activations Density 0.224%

    No Known Activations