© 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. 12301
    Prev
    Next
    INDEX
    Explanations

    modern and modernize

    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
    Negative Logits
    ntag
    -0.10
    cheap
    -0.09
    éħĿéħ¿
    -0.09
     seas
    -0.09
     cheap
    -0.09
    ä¾¿å®ľ
    -0.09
    eso
    -0.08
    isters
    -0.08
    iar
    -0.08
    å®īå±ħ
    -0.08
    POSITIVE LOGITS
     modern
    0.26
    çݰ代åĮĸ
    0.25
    modern
    0.24
    çݰ代
    0.24
    çı¾ä»£
    0.23
     moderne
    0.22
    ä¸İæĹ¶ä¿±è¿Ľ
    0.21
     ÑģовÑĢем
    0.20
    Modern
    0.20
     Modern
    0.20
    Activations Density 0.084%

    No Known Activations