© 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. 13073
    Prev
    Next
    INDEX
    Explanations

    contempt, disdain, disregard, scorn

    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
     зан
    -0.19
    à¹īาà¸ĩ
    -0.18
     Scouts
    -0.18
    aben
    -0.18
    éĤ¨
    -0.17
    æĦŁæħ¨
    -0.17
    Pri
    -0.17
    äºĨä¸ĢäºĽ
    -0.17
    åı¦ä¸Ģè¾¹
    -0.17
    hem
    -0.17
    POSITIVE LOGITS
    uous
    0.28
    uously
    0.23
    ably
    0.22
    ful
    0.21
    orary
    0.20
    ively
    0.20
    iar
    0.19
    oso
    0.19
    antly
    0.18
    ieux
    0.17
    Activations Density 0.002%

    No Known Activations