© 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. 267
    Prev
    Next
    INDEX
    Explanations

    URL fragments

    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
    Bounds
    -0.24
     bounds
    -0.23
    ób
    -0.22
     snd
    -0.22
    æľŃ
    -0.22
    Initialization
    -0.22
     boundaries
    -0.21
    beros
    -0.21
    .Lo
    -0.21
    ifiable
    -0.21
    POSITIVE LOGITS
     Sisters
    0.24
    大家åĪĨ享
    0.24
    ãĤ³ãĥ¬
    0.24
    ticket
    0.24
    bullet
    0.23
     Roose
    0.22
     Collector
    0.22
    主ä¹īæĢĿæĥ³
    0.22
    票
    0.22
    aar
    0.21
    Activations Density 0.076%

    No Known Activations