© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    quantity or cost

    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
    åħļåĨħ
    -0.26
    è¡¿
    -0.24
    åĺ¿åĺ¿
    -0.23
     Said
    -0.22
    å±ĤéĿ¢
    -0.22
    顶å±Ĥ设计
    -0.22
    è¿Ļè¯Ŀ
    -0.22
     withdrew
    -0.22
    /internal
    -0.21
    ernal
    -0.21
    POSITIVE LOGITS
    产åĩº
    0.28
    çĶ¨éĢĶ
    0.27
     potentially
    0.27
    åĽŀæĬ¥
    0.27
    Utility
    0.27
    æį¢æĿ¥
    0.26
    æľīçĶ¨
    0.25
    -risk
    0.25
     risk
    0.25
    ä¹°åĪ°
    0.25
    Activations Density 0.049%

    No Known Activations