© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15044
    Prev
    Next
    INDEX
    Explanations

    IP address configuration

    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
    çªĿ
    -0.24
    æľºæ¢°åĮĸ
    -0.23
    arov
    -0.22
    æ¼ķ
    -0.21
    _PED
    -0.20
    覺
    -0.20
     impeachment
    -0.20
    imd
    -0.20
    .pres
    -0.20
    headed
    -0.19
    POSITIVE LOGITS
    åıĺåĬ¨
    0.25
     ÑĤеле
    0.23
    ä¸Ĭç½ij
    0.22
    è¾ĥé«ĺçļĦ
    0.22
    advert
    0.22
     PropertyChanged
    0.21
     Internet
    0.21
    Disallow
    0.20
    身份
    0.20
    稳å®ļçļĦ
    0.20
    Activations Density 0.042%

    No Known Activations