© 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. 1184
    Prev
    Next
    INDEX
    Explanations

    cervical cancer and related conditions

    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
    orate
    -0.10
    èįı
    -0.09
    é¬ĵ
    -0.09
    rade
    -0.09
    æĭ³
    -0.09
    orman
    -0.09
    ÙĦات
    -0.09
    rid
    -0.08
    ulant
    -0.08
    Ùħت
    -0.08
    POSITIVE LOGITS
    嵬
    0.11
    qc
    0.08
    ailable
    0.08
    ãģĩ
    0.08
    itra
    0.08
    iasi
    0.08
    èĢIJå¿ĥ
    0.08
    zelf
    0.08
    pt
    0.08
    ä¸Ģ个æĺŁæľŁ
    0.08
    Activations Density 0.024%

    No Known Activations