© 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. 16726
    Prev
    Next
    INDEX
    Explanations

    mention or reference

    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
    è²Į
    -0.22
    æıIJä¾Ľä¼ĺè´¨
    -0.21
    大çīĩ
    -0.19
    建ç«ĭèµ·
    -0.19
    аÑĢа
    -0.18
    ળ
    -0.18
    _dup
    -0.18
     Yug
    -0.17
    inator
    -0.17
    elijk
    -0.17
    POSITIVE LOGITS
    æıIJåıĬ
    0.29
    åĩłæ¬¡
    0.24
     earlier
    0.23
     Mention
    0.22
    æıIJåĪ°
    0.21
    ä¸įæŃ¢
    0.21
    å¤ļ次
    0.21
    mention
    0.20
     mention
    0.20
     mentions
    0.20
    Activations Density 0.083%

    No Known Activations