© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 989
    Prev
    Next
    INDEX
    Explanations

    troubleshooting technical issues

    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
    Clause
    -0.24
    æľ¬éĴ±
    -0.23
    trait
    -0.23
    å°ĨæĿ¥
    -0.22
    èĩªæľī
    -0.22
    å°ĨæĪIJ为
    -0.21
    igraph
    -0.21
     rationale
    -0.21
    åİ¥
    -0.21
    èĩŃ
    -0.21
    POSITIVE LOGITS
     culprit
    0.41
    ä¸įå½ĵ
    0.37
    åı¯èĥ½åŃĺåľ¨
    0.33
     suspect
    0.32
     improperly
    0.32
     causing
    0.32
     suspected
    0.31
    æĺ¯åIJ¦åŃĺåľ¨
    0.31
    æĺ¯åIJ¦æľī
    0.31
     wrong
    0.30
    Activations Density 0.302%

    No Known Activations