© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15377
    Prev
    Next
    INDEX
    Explanations

    levels of difficulty

    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
    Evt
    -0.22
    nic
    -0.22
     hạ
    -0.20
    åĩłçĤ¹
    -0.19
    åģļä¸ĢäºĽ
    -0.19
     REPORT
    -0.19
     Contributors
    -0.19
    æŁIJäºĽ
    -0.18
    ä¼ĺåĬ¿
    -0.18
    overwrite
    -0.18
    POSITIVE LOGITS
    æ²³éģĵ
    0.22
    éĢļåħ³
    0.22
    å¯ĵ
    0.20
    _SO
    0.19
    æŀľ
    0.19
     Blond
    0.19
    ÑĤаÑĢ
    0.19
     kuk
    0.19
    éĤĪ
    0.19
    TED
    0.18
    Activations Density 0.015%

    No Known Activations