© 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. 12041
    Prev
    Next
    INDEX
    Explanations

    frequency or dosage intervals

    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
    pel
    -0.23
    夫人
    -0.21
    åĽŃ
    -0.20
    é£ŀ
    -0.20
    jan
    -0.19
    åıijåħī
    -0.19
    æĮ¥
    -0.18
     Degrees
    -0.18
    åħ±äº«
    -0.18
    .dispatch
    -0.18
    POSITIVE LOGITS
    éĹ´éļĶ
    0.27
    æĹ©æĻ¨
    0.23
    çĶ¨éĩı
    0.23
    潮湿
    0.21
    /logs
    0.20
    çĿ¡åīį
    0.20
    _bh
    0.20
     intervals
    0.20
    çĶ¨èį¯
    0.19
    ä¸ĬåѦ
    0.19
    Activations Density 0.039%

    No Known Activations