© 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. 31290
    Prev
    Next
    INDEX
    Explanations

    confiscate, seize property, garnishment

    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
     полÑĥÑĩа
    -0.10
    bour
    -0.10
    æľīæľºä¼ļ
    -0.09
    åĽłä¸ºæĪij
    -0.09
    getStore
    -0.09
    зав
    -0.09
    ysis
    -0.08
    imeo
    -0.08
    ä»ĸèĩªå·±
    -0.08
    èĻIJå¾ħ
    -0.08
    POSITIVE LOGITS
    äºĨ许å¤ļ
    0.09
    äºĨ大éĩıçļĦ
    0.09
    æ®Ĩ
    0.09
    äºĨä¸Ģæī¹
    0.09
    .dumps
    0.09
    outs
    0.08
    ä¸ĢåĪĩ
    0.08
     меди
    0.08
    æıĨ
    0.08
    edImage
    0.08
    Activations Density 0.012%

    No Known Activations