© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21174
    Prev
    Next
    INDEX
    Explanations

    lubricants and greases

    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
    åħ¬çĽĬ
    -0.09
    亥
    -0.09
    éĹ¹
    -0.09
    è·ĥ
    -0.09
    åīľ
    -0.09
    çĴĢçĴ¨
    -0.09
    èºį
    -0.09
    éϵ
    -0.09
    åį¯
    -0.08
    褫
    -0.08
    POSITIVE LOGITS
    èĨı
    0.11
    润æ»ij
    0.11
    æ¶ĤæĬ¹
    0.10
    åĬłæ²¹
    0.09
    é¢Ħéĺ²
    0.09
    æĥłåıĬ
    0.09
    ogne
    0.08
     grease
    0.08
    éĺ²æ°´
    0.08
    achi
    0.08
    Activations Density 0.074%

    No Known Activations