© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2126
    Prev
    Next
    INDEX
    Explanations

    timezones and locations

    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
    åĮĹæĸ¹
    -0.26
    ç»·
    -0.26
    åĽ½åĨħ
    -0.26
    .toArray
    -0.24
    åĽ½äº§
    -0.23
    *cos
    -0.23
    .tolist
    -0.23
    .ToArray
    -0.23
    è¶ĬåįĹ
    -0.23
    åĨħåľ°
    -0.23
    POSITIVE LOGITS
    æĻļæĬ¥
    0.27
    æ¯ıæĹ¥
    0.25
     timelines
    0.23
    åĩĮæĻ¨
    0.23
    iful
    0.22
    Chron
    0.22
    oton
    0.22
     fs
    0.21
    ilk
    0.21
    fsp
    0.21
    Activations Density 0.006%

    No Known Activations