© 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. 14701
    Prev
    Next
    INDEX
    Explanations

    cellular data consumption

    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
    åĿıäºĭ
    -0.24
    rig
    -0.23
    å±ģèĤ¡
    -0.21
    ç·´
    -0.21
    locked
    -0.20
    ç´ł
    -0.20
    ä¹ł
    -0.20
    ç¥Ŀè´º
    -0.19
     stiff
    -0.19
    colo
    -0.19
    POSITIVE LOGITS
    è´Łæĭħ
    0.29
    æī¿æĭħ
    0.27
    è´Łèį·
    0.26
    ä¸įåºĶ
    0.25
     burden
    0.23
    æī¿åıĹ
    0.23
     shouldn
    0.22
    ä¸įåºĶ该
    0.22
     strain
    0.21
    orry
    0.21
    Activations Density 0.210%

    No Known Activations