© 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. 15648
    Prev
    Next
    INDEX
    Explanations

    compelled violence or mental states

    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
    ä»¥äººä¸ºæľ¬
    -0.20
    澳大
    -0.20
    æįİ
    -0.20
    æİ¥åĬĽ
    -0.19
    åĬ¨æĢģ
    -0.19
    çī§åľº
    -0.19
    æıIJåĩºçļĦ
    -0.19
    éĩĮç¨ĭ
    -0.19
    åĽłä¸ºæĪij们
    -0.19
    éī´äºİ
    -0.18
    POSITIVE LOGITS
    iac
    0.23
    çĶļèĩ³è¿ŀ
    0.23
    åıĺå¾Ĺ
    0.23
    åĨįä¹Łä¸į
    0.20
     prog
    0.20
    åĨįä¹Ł
    0.19
    Revision
    0.19
    åıĺå¾ĹæĽ´åĬł
    0.19
     revision
    0.19
     verm
    0.19
    Activations Density 0.075%

    No Known Activations