© 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. 12721
    Prev
    Next
    INDEX
    Explanations

    preparation and completion

    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
    avn
    -0.21
    äºĨæĪijçļĦ
    -0.20
    读æĩĤ
    -0.19
     Flam
    -0.19
    ç©°
    -0.19
     UNC
    -0.19
    ycz
    -0.18
    aina
    -0.18
     Jay
    -0.18
    çľĭå¾Ĺ
    -0.18
    POSITIVE LOGITS
    åĩĨå¤ĩ
    0.26
    åĢĻ
    0.22
    åĩĨå¤ĩ好
    0.22
    çļĦè¿ĩç¨ĭä¸Ń
    0.21
    çħ®
    0.21
    ç©¿è¡£
    0.20
    åĬłçĥŃ
    0.20
    Processing
    0.19
     preparing
    0.19
    æºĸåĤĻ
    0.19
    Activations Density 0.025%

    No Known Activations