© 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. 468
    Prev
    Next
    INDEX
    Explanations

    years, initial, copyright

    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
    纬
    -0.26
    äºij
    -0.26
    anzi
    -0.23
    Dom
    -0.22
    _cloud
    -0.22
    YY
    -0.22
    cloud
    -0.22
     Cloud
    -0.22
    ave
    -0.21
     Dom
    -0.21
    POSITIVE LOGITS
    erge
    0.25
     swallow
    0.25
    åİŁå§ĭ
    0.24
    åľ¨æѤä¹ĭåīį
    0.24
     original
    0.24
     prefetch
    0.23
    :init
    0.23
     Initial
    0.23
    lasting
    0.22
    æľĢåĪĿçļĦ
    0.22
    Activations Density 0.062%

    No Known Activations