© 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. 13418
    Prev
    Next
    INDEX
    Explanations

    announces partnership 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
    ç¼Ł
    -0.20
     per
    -0.20
     thrown
    -0.20
     pos
    -0.20
     min
    -0.19
     fora
    -0.19
     possible
    -0.19
    ddl
    -0.19
     hard
    -0.18
    éŨåı£
    -0.18
    POSITIVE LOGITS
    该åħ¬åı¸
    0.23
    åħ¨çº¿
    0.23
    æݨåĩº
    0.22
    äº®çĽ¸
    0.22
    æłĩå¿ĹçĿĢ
    0.21
    æľįåĬ¡èĥ½åĬĽ
    0.21
    æݨåĩºäºĨ
    0.21
    ..↵↵↵↵
    0.21
    æĹĹä¸ĭ
    0.20
    åħ¨èµĦ
    0.20
    Activations Density 0.118%

    No Known Activations