© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30909
    Prev
    Next
    INDEX
    Explanations

    government actions and budgets

    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
    人çĶŁçļĦ
    -0.10
     Permanent
    -0.10
     permanent
    -0.10
    æľŁçĽ¼
    -0.10
    楼主
    -0.09
    èĩŃ
    -0.09
    lov
    -0.09
    æµģä¼ł
    -0.08
    åĴĮåıijå±ķ
    -0.08
    oden
    -0.08
    POSITIVE LOGITS
    主导
    0.10
    æľīèĥ½åĬĽ
    0.09
    -led
    0.09
    åľ¨ä¸ĢæĹģ
    0.09
    æıIJä¾ĽæĽ´å¤ļ
    0.08
    ä¿ļ
    0.08
    è´Ī
    0.08
    коÑģ
    0.08
    icable
    0.08
    bsp
    0.08
    Activations Density 0.043%

    No Known Activations