© 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. 12146
    Prev
    Next
    INDEX
    Explanations

    p.m. or a.m

    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
     fam
    -0.22
     original
    -0.20
     div
    -0.20
     fer
    -0.19
     depress
    -0.18
     ÐIJлекÑģан
    -0.18
    éĢĢå½¹
    -0.18
    à¸Ħà¸ĵะà¸ģรรม
    -0.18
    -f
    -0.18
     tre
    -0.18
    POSITIVE LOGITS
    å½±éŁ³
    0.20
    apesh
    0.20
    laces
    0.20
    åĬĽæ°Ķ
    0.20
    ฯ
    0.19
    æµ·éĩı
    0.19
     safezone
    0.19
    念头
    0.19
    èµ·åºĬ
    0.18
    æĪij们å¿ħé¡»
    0.18
    Activations Density 0.012%

    No Known Activations