© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16117
    Prev
    Next
    INDEX
    Explanations

    questions regarding issues or bugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    haven
    -0.21
    ikt
    -0.20
    oner
    -0.19
     Era
    -0.19
    ÑģпекÑĤ
    -0.19
    DON
    -0.18
    ate
    -0.18
    urg
    -0.18
    advert
    -0.18
    hot
    -0.18
    POSITIVE LOGITS
    请èģĶç³»
    0.22
    ä¼ļæľī
    0.20
    姥
    0.20
    佬
    0.20
    Unified
    0.20
    å·©
    0.20
    ä¸įåı¯éģ¿åħį
    0.19
    æĬ±æŃī
    0.19
    毫
    0.19
    æ¹¾åĮº
    0.18
    Activations Density 0.007%

    No Known Activations