© 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. 31025
    Prev
    Next
    INDEX
    Explanations

    new Bronson, hostiles, food &, Indian community, jazz and

    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
    ìŀIJìĿĺ
    -0.12
     ÑģобÑģÑĤвенно
    -0.10
    iets
    -0.10
    çļĦè¯Ŀ
    -0.10
    åŃ©åŃIJçļĦ
    -0.10
    çļĦäºĭ
    -0.10
    éļıåį³
    -0.10
    lıģın
    -0.10
    çļĦä¸ľè¥¿
    -0.10
    ÑĤай
    -0.10
    POSITIVE LOGITS
    æĤłä¹ħ
    0.10
    ç¦ıåĪ©
    0.09
    andard
    0.08
     contribution
    0.08
    对ä»ĸ们
    0.08
     inability
    0.08
    atest
    0.08
    æµ·å¤ĸå¸Ĥåľº
    0.08
    榻
    0.08
    tep
    0.08
    Activations Density 0.531%

    No Known Activations