© 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. 26255
    Prev
    Next
    INDEX
    Explanations

    following footsteps

    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
    æ²£
    -0.09
    æĢİä¹Īçľĭ
    -0.08
    åħīè¾ī
    -0.08
    ucha
    -0.08
    ä¹į
    -0.08
    æĢİä¹Ī
    -0.08
     lov
    -0.08
    æģ°
    -0.08
    滢
    -0.08
     Brooks
    -0.08
    POSITIVE LOGITS
    EDIA
    0.10
    åģļ个
    0.09
    ãģĹãģ¦
    0.09
    æĭįæĭį
    0.09
    AndGet
    0.09
    ·»
    0.09
    endir
    0.09
    áŀł
    0.09
    ICATION
    0.09
    umped
    0.09
    Activations Density 0.122%

    No Known Activations