© 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. 879
    Prev
    Next
    INDEX
    Explanations

    javadoc generation date

    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
    ÑĢеги
    -0.24
    .addTarget
    -0.24
    senal
    -0.23
    quo
    -0.23
     Hopkins
    -0.23
    isRequired
    -0.23
     cáºŃn
    -0.22
    ËĿ
    -0.22
    é¢Ĩ
    -0.22
    atories
    -0.22
    POSITIVE LOGITS
    æľįåĬ¡åĻ¨
    0.27
     uptime
    0.26
     WWW
    0.26
     ÑģеÑĢвеÑĢ
    0.26
     Powered
    0.25
     server
    0.25
    çīĪæĿĥå½Ĵ
    0.25
     caching
    0.25
    ìĭľìĬ¤íħľ
    0.25
     cached
    0.24
    Activations Density 0.039%

    No Known Activations