© 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. 657
    Prev
    Next
    INDEX
    Explanations

    regretting or informing about bad news

    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
    ç»ıæŁ¥
    -0.24
     Fever
    -0.23
    vsp
    -0.22
    å¥ĩå¦Ļ
    -0.22
     Sin
    -0.22
    å·¥ä½ľä½ľé£İ
    -0.22
    é¦ĭ
    -0.22
     Joint
    -0.22
    rex
    -0.22
     Pang
    -0.21
    POSITIVE LOGITS
    éģĹæĨ¾
    0.29
     disappoint
    0.29
     apologies
    0.29
     sadly
    0.29
    æŃī
    0.28
     unfortunately
    0.25
    ANTE
    0.24
     unavoidable
    0.24
    æĬ±æŃī
    0.24
    sorry
    0.23
    Activations Density 0.021%

    No Known Activations