© 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. 23768
    Prev
    Next
    INDEX
    Explanations

    energy and power sources

    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
    conc
    -0.10
     Wend
    -0.10
    æݧ
    -0.09
     conc
    -0.09
    é«ĺä»·
    -0.09
    æĬķèµĦ
    -0.09
    æIJŃ
    -0.09
    è´Ń
    -0.09
    è¾ķ
    -0.09
     sacks
    -0.08
    POSITIVE LOGITS
     powering
    0.09
    çħ§æĺİ
    0.09
    çļĦåĬ¨åĬĽ
    0.09
    æĬµæĬĹ
    0.08
    æĸŃ
    0.08
    _imm
    0.08
    éĹªçĥģ
    0.08
    è¿ŀå¤ľ
    0.08
    plat
    0.08
    iday
    0.08
    Activations Density 0.228%

    No Known Activations