© 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. 14048
    Prev
    Next
    INDEX
    Explanations

    study by researcher or firm

    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
    å¼ĥ
    -0.23
    æ£Ħ
    -0.20
    дол
    -0.19
    ÑģоÑģ
    -0.19
    moid
    -0.19
    ÑģÑħем
    -0.19
    dim
    -0.19
    empty
    -0.19
     Bbw
    -0.18
    URAL
    -0.18
    POSITIVE LOGITS
    æķ°æį®
    0.27
     data
    0.27
    æĬ¥åijĬæĺ¾ç¤º
    0.26
    æķ°æį®åĪĨæŀIJ
    0.26
    æķ°æį®æĺ¾ç¤º
    0.25
    çĽijæµĭ
    0.24
    åĪĨæŀIJ
    0.24
    çļĦæķ°æį®
    0.23
    æµĭç®Ĺ
    0.23
    ç»Łè®¡
    0.23
    Activations Density 0.077%

    No Known Activations