© 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. 3150
    Prev
    Next
    INDEX
    Explanations

    pixel size, density, resolution, MP

    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
    Vent
    -0.29
    helm
    -0.26
     Favor
    -0.24
    inded
    -0.23
    vent
    -0.23
     favor
    -0.22
     favour
    -0.22
    favor
    -0.22
    ä¸įäºĨ
    -0.22
     segreg
    -0.22
    POSITIVE LOGITS
    ixels
    0.35
    åĪĨ辨çİĩ
    0.33
    åĥıç´ł
    0.33
     pixels
    0.30
     densely
    0.30
     density
    0.30
     pixel
    0.30
    åĪĨ辨
    0.29
    pixels
    0.29
    åı·ç§°
    0.27
    Activations Density 0.023%

    No Known Activations