© 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. 16719
    Prev
    Next
    INDEX
    Explanations

    back to

    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
    ied
    -0.23
    oui
    -0.22
     pap
    -0.20
    eda
    -0.20
    och
    -0.19
     with
    -0.19
     worst
    -0.19
    æĸ½è¡Į
    -0.19
    ed
    -0.19
    enz
    -0.19
    POSITIVE LOGITS
    羣çĪ±
    0.21
    ãģ«æĪ»
    0.21
    ä¸Ĭæĸ¹
    0.21
    主页
    0.21
    æ»Ķ
    0.21
    æµĭè¯Ħ
    0.20
     ragaz
    0.20
    iếc
    0.20
    ä¹¡åľŁ
    0.20
    æĢĢæĬ±
    0.19
    Activations Density 0.005%

    No Known Activations