© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3407
    Prev
    Next
    INDEX
    Explanations

    spinal cord, integrated circuits, fat cells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     semi
    -0.24
    -s
    -0.24
    æĻ®æĥł
    -0.23
     conc
    -0.22
    iqu
    -0.22
    _intr
    -0.21
     "
    -0.21
    .g
    -0.21
    éĹŃçݯ
    -0.21
    AC
    -0.21
    POSITIVE LOGITS
    liness
    0.26
    ForObject
    0.25
     sexes
    0.23
    æľīçļĦ人
    0.23
    ToDevice
    0.23
    sites
    0.23
     Orchestra
    0.22
    LIK
    0.22
    ï¸
    0.22
     ltd
    0.22
    Activations Density 0.634%

    No Known Activations