© 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. 5454
    Prev
    Next
    INDEX
    Explanations

    law enforcement

    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
    楼ä¸ĭ
    -0.09
    apult
    -0.09
    æ¯Ķä¸Ĭå¹´
    -0.09
    ç³Ĭ
    -0.09
    åĭ¤å¥ĭ
    -0.09
    ety
    -0.08
    鸳
    -0.08
    è°Ģ
    -0.08
    bones
    -0.08
    絾
    -0.08
    POSITIVE LOGITS
    èĢħçļĦ
    0.11
    athe
    0.10
    rawn
    0.09
    人åijĺ
    0.09
    æ²Ļ
    0.08
    akers
    0.08
    å·¥ä½ľèĢħ
    0.08
    rians
    0.08
    èĢħ
    0.08
    acket
    0.08
    Activations Density 0.007%

    No Known Activations