© 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. 13705
    Prev
    Next
    INDEX
    Explanations

    buy, sell, or hold ratings

    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
    æľīå¿ħè¦ģ
    -0.21
    awi
    -0.21
     Cue
    -0.20
    .identity
    -0.20
    éŨæĪ·
    -0.20
    Identity
    -0.19
    ä¸ĢæīĢ
    -0.19
    ply
    -0.19
    çļĦéĢļçŁ¥
    -0.19
    oidal
    -0.18
    POSITIVE LOGITS
    åĥ¹
    0.21
    èĤ¡ç¥¨
    0.21
    çłĶ究åijĺ
    0.21
     Recomm
    0.21
     recomm
    0.21
    èįIJ
    0.19
     recomend
    0.19
    ä¸Ĭå¸Ĥ
    0.19
    è¾ĵ
    0.18
    ä¸Ĭè°ĥ
    0.18
    Activations Density 0.005%

    No Known Activations