© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29786
    Prev
    Next
    INDEX
    Explanations

    microwave, radio, oscillator, antenna, GHz

    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
    escal
    -0.10
    赶ä¸Ĭ
    -0.10
    æ¼Ĥæµģ
    -0.09
    ORB
    -0.09
    宣è¨Ģ
    -0.09
    è¡ĹåĮº
    -0.08
    çıŀ
    -0.08
    catch
    -0.08
    Catch
    -0.08
    票
    -0.08
    POSITIVE LOGITS
    éĵµ
    0.10
    è°ĭ
    0.09
    rowave
    0.09
    reeze
    0.09
    annie
    0.08
    ä¹ħä¹ħ
    0.08
    antine
    0.08
    _cs
    0.08
    æī©
    0.08
    ä¼Ĺ
    0.08
    Activations Density 0.171%

    No Known Activations