© 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. 1741
    Prev
    Next
    INDEX
    Explanations

    regret and disappointment

    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
     inquiry
    -0.24
     verbs
    -0.22
    út
    -0.22
    æ°ĵ
    -0.22
     Inquiry
    -0.22
    uD
    -0.22
     occult
    -0.21
     Customize
    -0.21
     glow
    -0.21
    -shadow
    -0.20
    POSITIVE LOGITS
    æĹłå¥Ī
    0.41
    ä½ĨçĶ±äºİ
    0.40
    å¾Īæĥ³
    0.34
    ä¸įæĦ¿æĦı
    0.33
    ç¢į
    0.33
    å°½éĩı
    0.33
     regret
    0.33
    ä¸įå¾Ĺå·²
    0.31
     regrets
    0.31
    æĦ¿æľĽ
    0.31
    Activations Density 0.138%

    No Known Activations