© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12500
    Prev
    Next
    INDEX
    Explanations

    legal/religious justification and righteousness

    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
    æ·±åĪ»çļĦ
    -0.19
    å¯Ŀ
    -0.19
    åĨ²éĶĭ
    -0.19
    é¼ĵåĬ±
    -0.18
    å¿łå®ŀ
    -0.18
    å§IJ妹
    -0.18
    æĦŁæŁĵèĢħ
    -0.18
    åIJ¯è¿ª
    -0.18
    家åĽŃ
    -0.18
    æĥľ
    -0.18
    POSITIVE LOGITS
    åĩºè·¯
    0.21
    _STRIP
    0.19
     ISSN
    0.19
    lers
    0.19
    anism
    0.19
    çĬ¶åħĥ
    0.18
     ineligible
    0.18
    åĬŁåĬ³
    0.18
    ä¸Ģä¸Ŀ
    0.18
    uggy
    0.18
    Activations Density 0.011%

    No Known Activations