© 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. 21214
    Prev
    Next
    INDEX
    Explanations

    any package?

    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
    _ctxt
    -0.10
    èľĥ
    -0.10
    èĦ±é¢ĸèĢĮåĩº
    -0.08
    wed
    -0.08
     зан
    -0.08
     only
    -0.08
    éĽª
    -0.08
     ctx
    -0.07
    妻
    -0.07
     Jacqu
    -0.07
    POSITIVE LOGITS
    ede
    0.10
    _ordered
    0.10
    /unit
    0.10
    é»ijé¾Ļ
    0.10
    bonus
    0.10
    enburg
    0.09
    itarian
    0.09
    驺
    0.09
    缴èIJ¥
    0.09
    è§Ĥèµı
    0.09
    Activations Density 0.009%

    No Known Activations