© 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. 13807
    Prev
    Next
    INDEX
    Explanations

    press conference or briefing

    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
     вообÑīе
    -0.20
    еÑĩа
    -0.19
    æľīæŶ
    -0.19
    ono
    -0.18
     nud
    -0.18
     gal
    -0.18
    valid
    -0.18
    ugal
    -0.17
    _THIS
    -0.17
    [((
    -0.17
    POSITIVE LOGITS
    äºĨä¸Ģ个
    0.22
    çļĦä¸Ģç§į
    0.20
    æľĢå¤ļçļĦ
    0.20
     same
    0.20
    æľĢç¾İ
    0.20
    æľĢ强
    0.20
    缸åºĶ
    0.20
    åĨįä¸Ģ次
    0.20
    çļĦä¸Ģ个
    0.19
    æľĢå¿«
    0.19
    Activations Density 0.680%

    No Known Activations