© 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. 3121
    Prev
    Next
    INDEX
    Explanations

    research results and breakthroughs

    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
     markdown
    -0.25
    verbatim
    -0.25
    поÑĤ
    -0.25
    Globals
    -0.24
     каÑĤегоÑĢии
    -0.23
     vÄĥn
    -0.23
    rete
    -0.23
    PageIndex
    -0.23
    TY
    -0.23
    å°½éĩı
    -0.23
    POSITIVE LOGITS
     breakthrough
    0.41
    çªģçł´
    0.39
    åĪĽéĢłåĩº
    0.38
    æĪIJæŀľ
    0.38
     experiments
    0.38
    å®ŀéªĮ
    0.38
    çłĶåĪ¶
    0.38
    æĶ»åħĭ
    0.38
     demonstrations
    0.35
     pioneering
    0.35
    Activations Density 0.103%

    No Known Activations