© 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. 63764
    Prev
    Next
    INDEX
    Explanations

    germinal center mutations

    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
    æĢ»éĺŁ
    -0.10
    ç§ijæĬĢ
    -0.09
    estone
    -0.09
    otime
    -0.09
    éķĿ
    -0.08
    åħ¬çº¦
    -0.08
    被害
    -0.08
    宾客
    -0.08
    æį
    -0.08
    oker
    -0.08
    POSITIVE LOGITS
    å°ģ
    0.09
    æľªç»ı
    0.09
    urat
    0.09
    è¡ĮæĶ¿åĮº
    0.09
    ष
    0.09
     thất
    0.09
    æŃ¤äºº
    0.08
    ÙģØ©
    0.08
    è´º
    0.08
    /tty
    0.08
    Activations Density 0.285%

    No Known Activations