© 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. 31083
    Prev
    Next
    INDEX
    Explanations

    feeling discomfort or being uncomfortable

    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
    éĮ¯
    -0.10
    ãģ¤ãĤĤãĤĬ
    -0.09
    çĭ®åŃIJ
    -0.09
    hev
    -0.09
    éĶĻ
    -0.09
    æģº
    -0.09
    epar
    -0.08
    endar
    -0.08
    èĵĿ天
    -0.08
    epend
    -0.08
    POSITIVE LOGITS
    Ñıд
    0.11
    çĶļèĩ³æĺ¯
    0.09
    æĸ¯åŁº
    0.09
    оÑĢÑĤ
    0.09
    _else
    0.08
    lix
    0.08
    annon
    0.08
     Hast
    0.08
    ä¸įå·²
    0.08
    illion
    0.08
    Activations Density 0.008%

    No Known Activations