© 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. 13706
    Prev
    Next
    INDEX
    Explanations

    reach or reaching goals

    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
    ãģĹãģ¾ãģĨ
    -0.18
     ello
    -0.16
    hoot
    -0.16
    chet
    -0.16
    amba
    -0.15
    æİī
    -0.15
    atures
    -0.15
    ships
    -0.15
    æĢį
    -0.15
    apolis
    -0.14
    POSITIVE LOGITS
    ieved
    0.21
    缮çļĦåľ°
    0.19
    è¦ģ害
    0.18
     adulthood
    0.17
    zeitig
    0.17
    -through
    0.17
    å¾Īé«ĺçļĦ
    0.17
    ings
    0.17
    ä¸įäºĨ
    0.17
    æľīä¸Ģ天
    0.17
    Activations Density 0.027%

    No Known Activations