© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22153
    Prev
    Next
    INDEX
    Explanations

    and, between, present

    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
    é¢ĺ主
    -0.09
    æįį
    -0.08
    ASY
    -0.08
    ä¹Ĵ
    -0.08
    ä¸Ģ举
    -0.08
    å§ŀ
    -0.08
    initely
    -0.08
    hir
    -0.08
    人å±ħ
    -0.08
    æĺ¯è¦ģ
    -0.08
    POSITIVE LOGITS
    误
    0.09
     ÑĤам
    0.08
    åģļä»Ģä¹Ī
    0.08
    à¹ģà¸ľ
    0.08
    äºĮåŃĹ
    0.08
    åħĢ
    0.08
    æĪ´ä¸Ĭ
    0.08
     [=
    0.08
    æİĸ
    0.08
    vette
    0.08
    Activations Density 0.577%

    No Known Activations