© 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. 19247
    Prev
    Next
    INDEX
    Explanations

    emergency evacuation threat drill

    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
    èĤ®
    -0.10
    ä¸į容æĺĵ
    -0.10
    åıĮè¾¹
    -0.10
    ç´łæĿIJ
    -0.09
    ä½
    -0.09
    пÑĢоÑģ
    -0.09
    æĭ¼
    -0.09
    ruise
    -0.09
    åĢĻ
    -0.08
    URNS
    -0.08
    POSITIVE LOGITS
    æ¼Ķç»ĥ
    0.12
    åħ¨æł¡
    0.12
    æ¼Ķä¹ł
    0.12
    çĸıæķ£
    0.10
    æıIJè´¨
    0.10
    åħ¨ä½ĵåijĺå·¥
    0.09
    å®ŀæĪĺ
    0.09
    éģ½
    0.09
    æĬ¥èѦ
    0.09
     Procedure
    0.08
    Activations Density 0.051%

    No Known Activations