© 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. 11988
    Prev
    Next
    INDEX
    Explanations

    applying safety programmes

    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
    çī¹èī²ç¤¾ä¼ļ
    -0.24
    throw
    -0.22
    ãģĹãģŁãģĵãģ¨
    -0.21
    distributed
    -0.21
    æķijçģ¾
    -0.20
    æīĭç»Ńè´¹
    -0.20
    annotate
    -0.20
    è´¸æĺĵæĪĺ
    -0.19
    çĻ»åľº
    -0.19
    mixed
    -0.19
    POSITIVE LOGITS
    æłĩåĩĨ
    0.26
    endant
    0.24
     sodom
    0.23
    åĽ½å®¶æłĩåĩĨ
    0.23
    æīĢæľīæĥħèĬĤ
    0.22
    æķ´æĶ¹
    0.22
    åŁºåĩĨ
    0.22
     пÑĢиÑıÑĤн
    0.22
    _mr
    0.21
    åIJĦ项
    0.21
    Activations Density 0.033%

    No Known Activations