© 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. 40378
    Prev
    Next
    INDEX
    Explanations

    footer / social links

    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
    麾
    -0.10
    æľªæĿ¥çļĦ
    -0.09
    avez
    -0.09
    rams
    -0.09
    /ne
    -0.09
    说åĪ°è¿ĻéĩĮ
    -0.09
    okie
    -0.09
    æľĢç»Ī
    -0.08
    å°ıç»Ħ
    -0.08
    еж
    -0.08
    POSITIVE LOGITS
    wards
    0.10
    ional
    0.09
    管å§Ķä¼ļ
    0.08
    chè
    0.08
    -most
    0.08
    æݨ
    0.08
    ascript
    0.08
    WARDS
    0.08
    ted
    0.08
    ä¸İåıijå±ķ
    0.08
    Activations Density 0.188%

    No Known Activations