© 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. 48507
    Prev
    Next
    INDEX
    Explanations

    electricity generation, power, and supply

    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
    åŃIJéĩĮ
    -0.10
    ood
    -0.09
    åļı
    -0.09
    itled
    -0.09
    erte
    -0.09
    맥
    -0.09
    åĨħçļĦ
    -0.09
    åĮ¹
    -0.08
    CTOR
    -0.08
    ings
    -0.08
    POSITIVE LOGITS
     thoại
    0.09
    scape
    0.09
    -minded
    0.08
    ¾
    0.08
    ally
    0.08
    ги
    0.08
    colo
    0.08
    pline
    0.08
    rieb
    0.08
    éĶĢåĶ®æĶ¶åħ¥
    0.08
    Activations Density 0.007%

    No Known Activations