© 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. 14626
    Prev
    Next
    INDEX
    Explanations

    no idea how

    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
    ä¸ĢåľĪ
    -0.20
    åĮĿ
    -0.18
    sta
    -0.18
    åĨįä¸Ģ次
    -0.18
    æŀģèĩ´
    -0.17
    ä¸Ŀä¸Ŀ
    -0.17
    çĶŁçĶŁ
    -0.16
    ç§ijåѦéĻ¢
    -0.16
    blr
    -0.16
    å¸ģ
    -0.16
    POSITIVE LOGITS
    ingly
    0.24
    /libs
    0.18
     Æ¡n
    0.17
    æĤĽ
    0.17
    repid
    0.17
    lessly
    0.17
    xia
    0.17
    -know
    0.17
     Happ
    0.16
    ç¦ĺ
    0.16
    Activations Density 0.007%

    No Known Activations