© 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. 15627
    Prev
    Next
    INDEX
    Explanations

    introduction, overlapping, mail, maps

    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
    æĺİæĺ¾çļĦ
    -0.18
    å¾Ĺèµ·
    -0.18
    åĴ¥
    -0.18
    ãģ«ãģªãĤĭãģ¨
    -0.17
    çļĦä¸ĵä¸ļ
    -0.17
    æĶ¾çľ¼
    -0.17
    åĭģ
    -0.17
    è¯Ħå®ļ
    -0.17
    unning
    -0.17
    (Process
    -0.16
    POSITIVE LOGITS
    éĺĥ
    0.21
     денег
    0.18
    çĻ¾è´§
    0.18
    çĥŃ带
    0.18
    ä¾ĽçĥŃ
    0.18
    é£İæĥħ
    0.18
    eki
    0.18
    orris
    0.17
    åŃ£èĬĤ
    0.17
    allo
    0.17
    Activations Density 0.003%

    No Known Activations