© 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. 15823
    Prev
    Next
    INDEX
    Explanations

    military sexual assaults

    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
    ird
    -0.21
    å¤ļæł·åĮĸ
    -0.20
    æľªæĿ¥åıijå±ķ
    -0.20
    èĩªæĿ¥
    -0.19
    è·Łå¥¹
    -0.18
    主åĬĽ
    -0.18
    UGH
    -0.18
    ãģĤãĤĮ
    -0.18
     onStop
    -0.18
     kut
    -0.17
    POSITIVE LOGITS
    管è¾ĸ
    0.24
    éĢĤçĶ¨
    0.23
    -covered
    0.23
     phạm
    0.22
    åıijçĶŁçļĦ
    0.22
    çī¹æ®ĬçļĦ
    0.22
    æŁ¥å¤Ħ
    0.22
     Special
    0.21
    åı¸æ³ķ
    0.21
    åIJĪæ³ķæĿĥçĽĬ
    0.21
    Activations Density 0.194%

    No Known Activations