© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 157
    Prev
    Next
    INDEX
    Explanations

    charges and fees

    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
    éĢĢå½¹
    -0.25
    wyn
    -0.24
    .loop
    -0.23
    æĶ¹èī¯
    -0.22
    åĪĨè£Ĥ
    -0.22
    UMENT
    -0.21
     iter
    -0.21
     gather
    -0.21
    åģĥ
    -0.21
    .rf
    -0.21
    POSITIVE LOGITS
    edImage
    0.29
    é«ĺæĺĤ
    0.28
    markup
    0.27
    .ast
    0.25
    æµ®åĬ¨
    0.24
     payable
    0.24
    çĶµè´¹
    0.24
     due
    0.24
    esc
    0.24
    edList
    0.24
    Activations Density 0.008%

    No Known Activations