© 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. 13987
    Prev
    Next
    INDEX
    Explanations

    whatever or somethin

    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
    åĶ¯ä¸ĢçļĦ
    -0.22
    _elem
    -0.21
    _warning
    -0.19
    é¹ĺ
    -0.19
     некоÑĤоÑĢÑĭÑħ
    -0.18
    é³Į
    -0.18
    éģ¿åŃķ
    -0.18
    è°ģèĥ½
    -0.18
    éric
    -0.17
    Decorator
    -0.17
    POSITIVE LOGITS
    æĢ»ä¹ĭ
    0.26
     whatever
    0.25
    whatever
    0.23
    ä¸į顾
    0.23
     Whatever
    0.22
    Whatever
    0.22
     else
    0.21
    åı°
    0.20
    else
    0.20
    åıįæŃ£
    0.19
    Activations Density 0.027%

    No Known Activations