© 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. 39894
    Prev
    Next
    INDEX
    Explanations

    promoter and reporter gene expression

    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
     capac
    -0.08
    çĴĭ
    -0.08
    åħħå®ŀ
    -0.08
    dragon
    -0.08
    微信åı·
    -0.08
    éºŁ
    -0.08
    ä¸įèĪį
    -0.08
     NET
    -0.08
    NET
    -0.08
    ç½ijä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æĭĺ
    0.10
     Cuomo
    0.09
    水管
    0.09
    滢
    0.09
    深度èŀįåIJĪ
    0.09
    æī§
    0.09
    oen
    0.09
    imately
    0.09
    æ´»åĬ¨ä¸Ń
    0.09
    æł¸å¿ĥåĮº
    0.09
    Activations Density 0.401%

    No Known Activations