© 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. 3102
    Prev
    Next
    INDEX
    Explanations

    if you have

    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
     Redistributions
    -0.25
    çļĦåŁºæľ¬
    -0.23
    è¿Ļæł·ä¸Ģ个
    -0.22
    æĺİæĺ¾çļĦ
    -0.22
    imes
    -0.21
     ih
    -0.21
    åĪĿ级
    -0.21
    mann
    -0.21
     either
    -0.20
    åŁºæľ¬
    -0.20
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.27
    åıĪèĥ½
    0.25
    AGER
    0.24
    åĽ¢åijĺ
    0.23
    uat
    0.22
    ä¹Łä¸įä¾ĭå¤ĸ
    0.22
     Genome
    0.22
    ä»Ģä¹Īéĥ½
    0.22
    _BP
    0.21
    ?action
    0.21
    Activations Density 0.243%

    No Known Activations