© 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. 34034
    Prev
    Next
    INDEX
    Explanations

    disability and health disorders

    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
    è´µ
    -0.11
    _mono
    -0.11
    ë°°
    -0.10
    çĤ¹å¤ļ
    -0.10
    好èݱåĿŀ
    -0.10
    çī¹æĿĥ
    -0.09
    æľįåĬ¡ä¸Ńå¿ĥ
    -0.09
    æĦŁæģ©
    -0.09
     беÑģплаÑĤ
    -0.09
    CTest
    -0.09
    POSITIVE LOGITS
    åĬ³åĬ¨åĬĽ
    0.10
    éļIJ
    0.09
     labor
    0.09
    5
    0.08
    座ä½į
    0.08
    irement
    0.08
    8
    0.08
    9
    0.08
    enton
    0.08
     Labor
    0.08
    Activations Density 0.141%

    No Known Activations