© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7987
    Prev
    Next
    INDEX
    Explanations

    academic terms

    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
    åIJİèĢħ
    -0.09
    å½ķ
    -0.09
     fold
    -0.09
    åŀĤ
    -0.09
    opa
    -0.09
    fold
    -0.08
    entina
    -0.08
     latter
    -0.08
    éĩijèŀįå¸Ĥåľº
    -0.08
    occo
    -0.08
    POSITIVE LOGITS
    æĴ®
    0.09
     помоÑīÑĮ
    0.09
     اÙĦدراسÙĬ
    0.09
     SSP
    0.09
    å½ĵä¹ĭ
    0.09
    åĽºä½ĵ
    0.09
    综åIJĪå¾ģ
    0.09
    å®ŀè·µç»ıéªĮ
    0.08
    reso
    0.08
    .static
    0.08
    Activations Density 0.098%

    No Known Activations