© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15128
    Prev
    Next
    INDEX
    Explanations

    sale and price events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     Fel
    -0.20
    ering
    -0.20
    oka
    -0.20
    amil
    -0.18
    æİ¥
    -0.18
     bip
    -0.17
    å¨ģ
    -0.17
    åĪĽ
    -0.17
     Wag
    -0.17
    WN
    -0.17
    POSITIVE LOGITS
    æľŁéĹ´
    0.29
    ulers
    0.24
    æ¸ł
    0.23
    å®ļä»·
    0.22
    åºĨåħ¸
    0.21
     markdown
    0.20
    åĵģç§į
    0.20
    -priced
    0.20
    æĶ¾åĩº
    0.20
    annies
    0.20
    Activations Density 0.012%

    No Known Activations