© 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. 54036
    Prev
    Next
    INDEX
    Explanations

    success

    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
    éŀŃ
    -0.10
    对å¾ħ
    -0.09
     ÄijoÃłn
    -0.09
    obox
    -0.09
     hạt
    -0.09
    è·ĥ
    -0.09
    絾
    -0.09
    лез
    -0.09
    à¹Ħà¸Ĥ
    -0.09
     تÙĤدÙĬ
    -0.08
    POSITIVE LOGITS
     success
    0.25
    æĪIJåĬŁ
    0.25
    çļĦæĪIJåĬŁ
    0.24
    æĪIJåĬŁçļĦ
    0.23
    失败
    0.22
    success
    0.21
     succeed
    0.20
     successful
    0.19
    -success
    0.18
    Success
    0.18
    Activations Density 0.083%

    No Known Activations