© 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. 26197
    Prev
    Next
    INDEX
    Explanations

    asking "lord" or "god"

    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
    é¦Ĵ
    -0.08
     alt
    -0.08
    funcs
    -0.08
     Hamm
    -0.08
    lector
    -0.08
    pire
    -0.08
    ç¿Ļ
    -0.08
    æĦŁ
    -0.08
     ah
    -0.07
    (*)(
    -0.07
    POSITIVE LOGITS
    éªĪ
    0.10
    æ±Ĥ
    0.09
    åŀĤ
    0.09
    asca
    0.09
    åıĮåIJij
    0.09
    çIJĥåľº
    0.09
    èĤ«
    0.09
    Subsystem
    0.09
    åģļ个
    0.09
    ITT
    0.09
    Activations Density 0.030%

    No Known Activations