© 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. 1055
    Prev
    Next
    INDEX
    Explanations

    because

    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
    为ä»Ģä¹Īä¼ļ
    -0.29
    ä¹ĭæĺŁ
    -0.26
    decision
    -0.26
    å©ļåIJİ
    -0.25
    stringValue
    -0.25
    ä¹ĭæīĢ以
    -0.24
    èĥ½åľ¨
    -0.23
    éĢłç¦ı
    -0.23
    没éĶĻ
    -0.23
    å½ĵä½ł
    -0.22
    POSITIVE LOGITS
     lack
    0.33
    缺ä¹ı
    0.32
    èĢĮæĺ¯
    0.32
     nor
    0.31
     already
    0.30
    éĻ¤éĿŀ
    0.29
     busy
    0.29
     fear
    0.28
    害æĢķ
    0.28
    æĺ¯éĿŀ
    0.28
    Activations Density 0.083%

    No Known Activations