© 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. 14122
    Prev
    Next
    INDEX
    Explanations

    in conjunction with

    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
    semble
    -0.20
    ³
    -0.19
    opts
    -0.18
    æľīä¸Ģ次
    -0.18
     somewhere
    -0.18
    æĬľ
    -0.18
    CLE
    -0.18
    ä¸į管æĺ¯
    -0.18
    è¯Ŀ
    -0.17
    éĹ®é¢ĺæĺ¯
    -0.17
    POSITIVE LOGITS
    åħ¶ä»ĸ人
    0.31
    åħ¶å®ĥ
    0.28
    æĪij们ä¸Ģèµ·
    0.24
    åħ¶ä»ĸçļĦ
    0.23
    ä»ĸ人
    0.22
    åħ¶ä»ĸ
    0.22
    å°ıç¼ĸä¸Ģèµ·
    0.21
    åı¦ä¸Ģä½į
    0.21
    çıł
    0.20
     others
    0.20
    Activations Density 0.014%

    No Known Activations