© 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. 16840
    Prev
    Next
    INDEX
    Explanations

    nucleus neurons

    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
     JK
    -0.10
     wards
    -0.08
     coinc
    -0.08
     coincidence
    -0.08
     knocks
    -0.08
    æ·¤
    -0.08
    秣
    -0.08
    GOR
    -0.08
    _PORTS
    -0.08
    POCH
    -0.08
    POSITIVE LOGITS
    éºŁ
    0.10
    çĿģå¼Ģ
    0.10
    ä¹Ĵä¹ĵ
    0.10
    blink
    0.09
    çĿģ
    0.09
     hÆ°á»Łng
    0.09
    èĪĮ头
    0.09
    æĪijçľĭ
    0.09
    ipel
    0.09
    鸳
    0.09
    Activations Density 0.389%

    No Known Activations