© 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. 35138
    Prev
    Next
    INDEX
    Explanations

    electrical rates and prices

    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
    æ·Į
    -0.09
    èĥ¡åIJĮ
    -0.09
    åŃĺéĩı
    -0.09
    æĹ¶è¾°
    -0.08
    Gift
    -0.08
    æĢ»èµĦ产
    -0.08
    çĦķ
    -0.08
    åīįä¸ī
    -0.08
    rior
    -0.08
    _motion
    -0.08
    POSITIVE LOGITS
    ä»·æł¼ä¸Ĭ涨
    0.20
    çī©ä»·
    0.17
    ä¸Ĭ涨
    0.16
    ä»·æł¼
    0.16
     prices
    0.16
    涨价
    0.15
    ä»·éĴ±
    0.15
     ÑĨенÑĭ
    0.15
    prices
    0.15
    油价
    0.13
    Activations Density 0.078%

    No Known Activations