© 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
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 99
    Prev
    Next
    INDEX
    Explanations

    enlighten and illuminate

    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
    -quarters
    -0.22
    gone
    -0.22
    ity
    -0.21
    inals
    -0.21
     Tos
    -0.20
    çľģåĨħ
    -0.19
    æłĹ
    -0.19
    chten
    -0.19
    agon
    -0.19
    .readyState
    -0.19
    POSITIVE LOGITS
    /disable
    0.27
    enment
    0.26
    anter
    0.24
    人士
    0.23
    oir
    0.22
    æĤŁ
    0.21
     Ñģобой
    0.21
    äºĭä¸ļ
    0.20
    èĢħçļĦ
    0.20
     سبÙĬÙĦ
    0.20
    Activations Density 0.013%

    No Known Activations