© 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. 53741
    Prev
    Next
    INDEX
    Explanations

    hand or left

    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
    çĥ¦æģ¼
    -0.10
    å±ĭéĩĮ
    -0.09
    çĥĪ
    -0.09
    assy
    -0.09
    ayer
    -0.09
    /{{
    -0.09
    å±ĭ
    -0.09
    creds
    -0.09
    æĹı
    -0.09
    é©¿ç«Ļ
    -0.09
    POSITIVE LOGITS
    çīµæīĭ
    0.13
    æIJº
    0.11
    æİĩ
    0.10
    çī½
    0.10
    çĹŀ
    0.10
    æĭ½
    0.10
    ä¸Ģæīĭ
    0.10
    ç¬ijçĿĢ
    0.09
     hand
    0.09
    æĮ½
    0.09
    Activations Density 0.018%

    No Known Activations