© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2951
    Prev
    Next
    INDEX
    Explanations

    final moments or periods

    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
    å¾Īå¿«
    -0.26
     Soon
    -0.26
     pronto
    -0.26
    å½ĵåį³
    -0.26
     Immediately
    -0.25
     immediate
    -0.25
     immediately
    -0.24
    å¾Īå¿«å°±
    -0.24
     yarı
    -0.24
     Quickly
    -0.23
    POSITIVE LOGITS
    Throughout
    0.43
     throughout
    0.42
     Throughout
    0.41
     final
    0.40
    åİĨæŶ
    0.38
    æľĢåIJİä¸Ģ
    0.37
    çļĦæľĢåIJİä¸Ģ
    0.36
    -final
    0.34
    ç»ĵæĿŁ
    0.34
     accumulated
    0.34
    Activations Density 0.206%

    No Known Activations