© 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. 40092
    Prev
    Next
    INDEX
    Explanations

    Jesus Christ

    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
    缺åı£
    -0.10
    agn
    -0.10
    edList
    -0.10
    edException
    -0.10
    amp
    -0.09
    éĶ·
    -0.09
    aat
    -0.09
    ers
    -0.09
    å¦ĩèģĶ
    -0.09
    åĴİ
    -0.09
    POSITIVE LOGITS
    åŁºçĿ£
    0.14
     Christ
    0.10
    arez
    0.09
    amine
    0.09
    æł·çļĦ
    0.09
     Ñģобой
    0.09
    ingle
    0.08
    TokenType
    0.08
    omid
    0.08
    ropa
    0.08
    Activations Density 0.009%

    No Known Activations