© 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. 11652
    Prev
    Next
    INDEX
    Explanations

    better or best choice

    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
    è´©åįĸ
    -0.20
    åĬ¨çĶŁæĪIJ
    -0.19
    .Transport
    -0.18
    åIJįåĪĹ
    -0.18
    .Compute
    -0.18
     легко
    -0.18
    è§īå¾Ĺå¾Ī
    -0.17
    invalidate
    -0.17
    Assignable
    -0.17
    æ§Ľ
    -0.17
    POSITIVE LOGITS
    ä¸įå®ľ
    0.23
    éģĤ
    0.21
    稳妥
    0.20
    å®ŀè¡Į
    0.20
     suited
    0.20
    éķ¿è¿ľ
    0.20
    å®ŀæĸ½æĸ¹æ¡Ī
    0.19
    åĺĺ
    0.19
    åıįèĢĮ
    0.19
    æĸ¹æ¡Ī
    0.19
    Activations Density 0.092%

    No Known Activations