© 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. 8986
    Prev
    Next
    INDEX
    Explanations

    extra-large, oversized, size, life

    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
    fully
    -0.13
    lessly
    -0.10
    女ç¥ŀ
    -0.09
    çIJ´
    -0.09
    å©ī
    -0.09
    oleon
    -0.08
    orie
    -0.08
    å½ĵåľ°æĶ¿åºľ
    -0.08
    spot
    -0.08
    ãĤıãģļ
    -0.08
    POSITIVE LOGITS
    -sized
    0.11
    åĨĪ
    0.09
     sized
    0.09
    ature
    0.09
    atures
    0.09
    æĪ¬
    0.09
    mant
    0.08
    åĬª
    0.08
    apan
    0.08
    avo
    0.08
    Activations Density 0.013%

    No Known Activations