© 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. 14225
    Prev
    Next
    INDEX
    Explanations

    bath and body works

    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
    éĿ¢åŃĶ
    -0.23
    头
    -0.22
    天èĬ±
    -0.21
    缮çĿ¹
    -0.20
     глаз
    -0.20
     Pres
    -0.20
    äº²çľ¼
    -0.20
    订
    -0.20
    çľ¼éķľ
    -0.20
    èĪĮ
    -0.19
    POSITIVE LOGITS
    èĤĮèĤ¤
    0.26
    çļ®èĤ¤
    0.26
    æķ´ä¸ªäºº
    0.23
    èĤ¤
    0.22
    大çīĩ
    0.20
    液
    0.20
    _SO
    0.20
    类产åĵģ
    0.19
    èĨ
    0.19
     skin
    0.19
    Activations Density 0.007%

    No Known Activations