© 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. 38183
    Prev
    Next
    INDEX
    Explanations

    closing braces and brackets

    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
     inexp
    -0.08
     lẽ
    -0.08
    ×Ļף
    -0.08
    åŀĴ
    -0.07
    éŨæĪ·
    -0.07
     *[
    -0.07
    istine
    -0.07
    çī¹åĪ«æĺ¯
    -0.07
    鸳
    -0.07
    éĩĬ
    -0.07
    POSITIVE LOGITS
    ettes
    0.10
    渤海
    0.09
    etto
    0.09
    çŁĽçĽ¾
    0.09
    èģª
    0.09
    çĴŀ
    0.09
    UEST
    0.09
    ä¸įæĸŃåĪĽæĸ°
    0.09
    é«Ń
    0.08
    edith
    0.08
    Activations Density 0.540%

    No Known Activations