© 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. 2513
    Prev
    Next
    INDEX
    Explanations

    gamma, alpha, beta

    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
    ç«ŀ
    -0.10
    æŸ
    -0.09
    antu
    -0.09
    éī´
    -0.09
    饯
    -0.09
    çijķ
    -0.08
    ordan
    -0.08
    orman
    -0.08
    çIJħ
    -0.08
    pek
    -0.08
    POSITIVE LOGITS
    å®£ä¼łæķĻèĤ²
    0.09
    é£Ľãģ³
    0.08
    åĴĮåħ¶ä»ĸ
    0.08
    æŀī
    0.08
     firma
    0.08
    åıĬåħ¶ä»ĸ
    0.08
    dsa
    0.08
    GLOBALS
    0.08
     Kaplan
    0.08
    主è¦ģåĨħ容
    0.08
    Activations Density 0.510%

    No Known Activations