© 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. 15724
    Prev
    Next
    INDEX
    Explanations

    child seat

    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
    çĭĤ
    -0.19
    æ»ĭ
    -0.19
    éĩİçĶŁ
    -0.18
    âĮł
    -0.18
    ]|[
    -0.18
    .asc
    -0.18
    åĨįçĶŁ
    -0.18
    UGH
    -0.17
    çģ«çĥ§
    -0.17
    ampoo
    -0.17
    POSITIVE LOGITS
    å¹´é¾Ħ
    0.29
    å¹´é¾Ħ段
    0.28
    çļĦå®īåħ¨
    0.28
    çĽijæĬ¤
    0.27
    æĤ¨çļĦåŃ©åŃIJ
    0.27
    çļĦåŃ©åŃIJ
    0.26
    è´Ń票
    0.25
    身é«ĺ
    0.25
    姿åĬ¿
    0.25
    座ä½į
    0.25
    Activations Density 0.015%

    No Known Activations