© 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. 16233
    Prev
    Next
    INDEX
    Explanations

    exposure to agents

    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´ŀ
    -0.20
     Ñģобой
    -0.19
    бÑĥÑĢ
    -0.19
    ValuePair
    -0.18
    åĸĦäºİ
    -0.18
    åĩºäºĨ
    -0.17
    éĹ³
    -0.17
     Inner
    -0.17
    è¿ĽåĨĽ
    -0.17
    istr
    -0.17
    POSITIVE LOGITS
    tems
    0.20
    å¾ĪæŃ£å¸¸
    0.19
    åı¯èĥ½åıijçĶŁ
    0.18
    æĥħåĨµ
    0.18
    æĮ«æĬĺ
    0.18
    hip
    0.17
     lapse
    0.17
    ģ
    0.17
    åĽłç´ł
    0.17
     hazard
    0.17
    Activations Density 0.037%

    No Known Activations