© 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. 54438
    Prev
    Next
    INDEX
    Explanations

    without further

    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
    ТÐĺ
    -0.10
    ewood
    -0.09
    íĮħ
    -0.09
    acey
    -0.08
     każdego
    -0.08
    åIJĦ个æĸ¹éĿ¢
    -0.08
    溢价
    -0.08
    ä¸įä»ħ
    -0.08
    åijµ
    -0.08
    interp
    -0.08
    POSITIVE LOGITS
     proper
    0.11
    çļĦè¯Ŀ
    0.09
    驺
    0.09
    usses
    0.09
    æIJŀ好
    0.09
    é«ĺ涨
    0.09
    åĿļ强
    0.09
    çľģ级
    0.09
    对æ¯Ķ
    0.09
     Proper
    0.09
    Activations Density 0.026%

    No Known Activations