© 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. 53396
    Prev
    Next
    INDEX
    Explanations

    inbreeding, consanguineous, mixture, linkage, intermixing

    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
    oha
    -0.09
    å¹´èĸª
    -0.09
    èĿĩ
    -0.09
    nie
    -0.09
    ç»ĵå±Ģ
    -0.09
     variant
    -0.09
     Variant
    -0.09
    å¾Ĵ
    -0.09
    åħ¨èµĦ
    -0.09
    åħļçļĦ建设
    -0.09
    POSITIVE LOGITS
    æݨ
    0.09
    è¦ģ注æĦı
    0.08
     Ax
    0.08
     Edgar
    0.08
    éĢı
    0.08
    åıªæĺ¯
    0.08
    缩å°ı
    0.08
    éŀį
    0.08
    7
    0.08
    uttgart
    0.07
    Activations Density 0.135%

    No Known Activations