© 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. 20456
    Prev
    Next
    INDEX
    Explanations

    apologize for, withdraw

    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
    çŁ¿åĮº
    -0.10
    ODB
    -0.09
    èĢĮéĿŀ
    -0.09
    èĭ±
    -0.08
    é¬ĵ
    -0.08
    àºĩ
    -0.08
    åĬ±
    -0.08
    æł·çļĦ
    -0.08
    鲸
    -0.08
    hab
    -0.08
    POSITIVE LOGITS
    æĮĩå°ĸ
    0.11
    佶
    0.10
    statement
    0.09
    æĴ¤
    0.09
    åıijå¸ĥ
    0.09
    迤
    0.09
    éħ¤
    0.09
    è´¿
    0.09
    éĴ¿
    0.09
     gag
    0.09
    Activations Density 0.043%

    No Known Activations