© 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. 12802
    Prev
    Next
    INDEX
    Explanations

    software utilities and tools

    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
    çĬĬ
    -0.21
    åĬ²
    -0.21
    æİ¢
    -0.20
    åĤ¨å¤ĩ
    -0.19
    _NR
    -0.19
    ä¸Ģéĺµ
    -0.19
    é¢Ĩ
    -0.19
    iate
    -0.18
    æŁł
    -0.18
    ç©¿è¶Ĭ
    -0.18
    POSITIVE LOGITS
    æIJ¦
    0.19
    åħī
    0.19
    讲æķħäºĭ
    0.18
    ault
    0.18
    ijd
    0.18
    ï¸ı
    0.18
    isoft
    0.17
    obil
    0.17
    mediately
    0.17
    imin
    0.17
    Activations Density 0.020%

    No Known Activations