© 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. 16584
    Prev
    Next
    INDEX
    Explanations

    bronze medal

    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
    ç§
    -0.23
    æĹłç¼Ŀ
    -0.22
    ycz
    -0.20
    çļĦä¼ĺçĤ¹
    -0.19
    éķ¿éĢĶ
    -0.19
    ä¼ĺçĤ¹
    -0.19
    ä¼ĺåĬ¿
    -0.19
    éķ¿å¤§äºĨ
    -0.19
     advantage
    -0.19
     Crack
    -0.19
    POSITIVE LOGITS
    çĦIJ
    0.21
    æķijæµİ
    0.21
    æħ°
    0.20
    nge
    0.20
    æĤ»
    0.20
    ivec
    0.20
    onga
    0.19
    éĩijåŃĹå¡Ķ
    0.19
    å¥Ĥ
    0.19
    åıįæŃ£
    0.19
    Activations Density 0.014%

    No Known Activations