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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 0
    Prev
    Next
    INDEX
    Explanations

    final

    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
    åĪĿæŃ¥
    -0.30
    åĪĿæľŁ
    -0.25
     Nar
    -0.25
    .Initial
    -0.24
    initial
    -0.24
     initial
    -0.23
    _INITIAL
    -0.23
     oblig
    -0.23
    _ORIGIN
    -0.23
    å°½æĹ©
    -0.23
    POSITIVE LOGITS
    æľĢåIJİä¸Ģ
    0.80
     final
    0.75
    æľĢåIJİä¸Ģ个
    0.73
    çļĦæľĢåIJİä¸Ģ
    0.72
    æľĢåIJİ
    0.72
    æľĢåIJİä¸Ģ次
    0.69
    .final
    0.65
    final
    0.65
    æľĢå¾Į
    0.64
    æĶ¶å®ĺ
    0.63
    Activations Density 0.255%

    No Known Activations