© 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. 22812
    Prev
    Next
    INDEX
    Explanations

    BRCA1/BRCA2 cancer susceptibility

    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
    eced
    -0.10
    .jasper
    -0.09
    å¹´ç»Ī
    -0.09
    åīįä¸ī
    -0.09
    èŀį
    -0.09
    å®ł
    -0.09
    æĶ¶ç¼©
    -0.08
    akan
    -0.08
    ç
    -0.08
    _delivery
    -0.08
    POSITIVE LOGITS
     vigil
    0.10
    å°±æѤ
    0.09
    åij¤
    0.09
    æĪª
    0.09
    å¯¹æľªæĿ¥
    0.09
    .onStart
    0.09
    orf
    0.09
    wang
    0.08
    èĢģ人家
    0.08
    ä¹³æĪ¿
    0.08
    Activations Density 0.141%

    No Known Activations