© 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. 649
    Prev
    Next
    INDEX
    Explanations

    admitted not prior art

    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
    çŃīçĿĢ
    -0.26
    åIJİå¤ĩ
    -0.25
    åĩºéģĵ
    -0.23
    ä»İå°ı
    -0.23
    åįģä½³
    -0.23
    æ¯ķä¸ļçĶŁ
    -0.23
    Enterprise
    -0.23
    æķĪçİĩ
    -0.22
    好人
    -0.22
    æ±ĩéĽĨ
    -0.22
    POSITIVE LOGITS
    æī¿è®¤
    0.33
     acknowledge
    0.30
    ack
    0.29
     acknowledging
    0.28
    _ACK
    0.28
     пÑĢизна
    0.28
    ACK
    0.28
    认åIJĮ
    0.28
     acknowledged
    0.27
     Ack
    0.27
    Activations Density 0.014%

    No Known Activations