© 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. 33942
    Prev
    Next
    INDEX
    Explanations

    electrical 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
    cheng
    -0.10
    åįİ侨
    -0.10
    .bounds
    -0.10
    åı¸
    -0.10
    tring
    -0.09
    èĢģ人
    -0.09
    ç®Ķ
    -0.09
    lify
    -0.09
    æıŃ
    -0.08
    _MAXIMUM
    -0.08
    POSITIVE LOGITS
    容éĩı
    0.10
    çĶµæºIJ
    0.10
    çĶµç½ij
    0.09
     cottage
    0.09
    facet
    0.09
    åħ¨æĻ¯
    0.09
     rede
    0.08
    à¹Ģà¸Ĺ
    0.08
    essen
    0.08
    æĻ®éĢļçļĦ
    0.08
    Activations Density 0.047%

    No Known Activations