© 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. 560
    Prev
    Next
    INDEX
    Explanations

    tax cuts, hikes, and incentives

    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
    éķĿ
    -0.25
     ach
    -0.24
     unw
    -0.23
    fang
    -0.23
    thing
    -0.22
     adher
    -0.22
    zza
    -0.21
    chaft
    -0.21
     unp
    -0.21
    Glass
    -0.20
    POSITIVE LOGITS
    å¹ħ度
    0.38
    åĬĽåº¦
    0.23
    å¾ħéģĩ
    0.23
    å©ļ
    0.22
    æĿ¡æ¬¾
    0.22
    裤
    0.22
    upported
    0.22
     publicity
    0.22
    åĬ£
    0.22
    æĶ¿
    0.21
    Activations Density 0.006%

    No Known Activations