© 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. 3126
    Prev
    Next
    INDEX
    Explanations

    MAC and conference abbreviations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    igue
    -0.23
    umble
    -0.22
    hood
    -0.22
    heits
    -0.22
    æłİ
    -0.22
    åľŃ
    -0.21
    urname
    -0.21
    è¡·
    -0.21
    here
    -0.21
    olute
    -0.21
    POSITIVE LOGITS
    sWith
    0.27
    lâ
    0.25
    ä¼łåĩº
    0.23
    ä¸Ĭä¼ł
    0.23
    æķ·
    0.22
    è§ģåĪ°
    0.21
    sheet
    0.21
    ä¼łæĿ¥
    0.20
     deport
    0.20
    sel
    0.20
    Activations Density 0.002%

    No Known Activations