© 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. 3201
    Prev
    Next
    INDEX
    Explanations

    close or narrow margins

    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
    çĩĶ
    -0.24
    CS
    -0.23
    ugen
    -0.23
    roots
    -0.23
    è°£
    -0.22
     Fucking
    -0.22
    Laugh
    -0.21
    vature
    -0.21
    æĸĩ娱
    -0.21
    (chr
    -0.21
    POSITIVE LOGITS
    ç»Ĩå¾®
    0.29
     borderline
    0.28
     tight
    0.26
    ç²¾å¯Ĩ
    0.24
    åĨ³çŃĸ
    0.24
    åĴ«
    0.24
     hanging
    0.23
    çĬ¹è±«
    0.23
    å°ıäºĭ
    0.23
     narrow
    0.23
    Activations Density 0.077%

    No Known Activations