© 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. 31825
    Prev
    Next
    INDEX
    Explanations

    world of

    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
    éĢĢ
    -0.09
     going
    -0.09
    ghi
    -0.09
    -going
    -0.08
    åľŃ
    -0.08
    æľīæīĢ
    -0.08
    纵åIJij
    -0.08
    going
    -0.08
    详
    -0.08
     prop
    -0.08
    POSITIVE LOGITS
     realm
    0.14
    ä¸ĸçķĮçļĦ
    0.14
     миÑĢ
    0.13
    ä¸ĸçķĮ
    0.12
     world
    0.12
    ä¸ĸéĹ´
    0.11
    ä¸ĸçķĮä¸Ĭ
    0.11
    realm
    0.11
    oser
    0.11
     mondo
    0.11
    Activations Density 0.081%

    No Known Activations