© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61398
    Prev
    Next
    INDEX
    Explanations

    immune regulation and tolerance

    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
    tap
    -0.09
    ç´§
    -0.09
    ç´§å¯Ĩ
    -0.09
    æĪIJ绩
    -0.09
    alers
    -0.08
    紧紧
    -0.08
    ç·Ĭ
    -0.08
    æĶ¶ç´§
    -0.08
    åħĪ导
    -0.08
    交æĺĵæīĢ
    -0.08
    POSITIVE LOGITS
    宽容
    0.18
    peace
    0.16
     peace
    0.15
    åĴĮå¹³
    0.14
    Peace
    0.13
     peaceful
    0.13
     tolerance
    0.13
    åĮħ容
    0.13
     peacefully
    0.12
    åĴĮçĿ¦
    0.12
    Activations Density 0.199%

    No Known Activations