© 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. 843
    Prev
    Next
    INDEX
    Explanations

    names or titles followed by punctuation

    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
    Whilst
    -0.31
     Whilst
    -0.26
    /uploads
    -0.26
    etten
    -0.25
    ç»Ŀ对
    -0.24
     onboard
    -0.24
    .rpm
    -0.23
    /demo
    -0.23
     Aussie
    -0.23
    MMM
    -0.23
    POSITIVE LOGITS
     NYT
    0.32
     Slate
    0.27
    纽约
    0.25
     Bloomberg
    0.25
     Princeton
    0.24
     Pulitzer
    0.24
     Whitney
    0.23
     absl
    0.23
    {{
    0.23
    Č↵
    0.23
    Activations Density 0.156%

    No Known Activations