© 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. 16641
    Prev
    Next
    INDEX
    Explanations

    stealing or taking items

    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
    å¼ı
    -0.22
    å£ģ
    -0.21
     bombard
    -0.21
    å¯Įè£ķ
    -0.20
    æĬĬèĩªå·±çļĦ
    -0.20
    æķ²
    -0.20
    /vnd
    -0.19
    èĥ½èĢĹ
    -0.19
     trải
    -0.18
    å¦ĵ
    -0.18
    POSITIVE LOGITS
    leave
    0.22
    éļıåIJİ
    0.22
     khá»ıi
    0.22
    两åIJį
    0.21
     contents
    0.21
    ious
    0.21
    å½ĵæĻļ
    0.21
    èĢĮåİ»
    0.20
    离å¼ĢäºĨ
    0.20
    ophone
    0.20
    Activations Density 0.014%

    No Known Activations