© 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. 12494
    Prev
    Next
    INDEX
    Explanations

    firefighter and fire department

    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
    .hr
    -0.21
    éĤ®å¯Ħ
    -0.21
    outing
    -0.20
     transplantation
    -0.20
    è¿ĩåħ³
    -0.19
    lobal
    -0.19
    mousemove
    -0.19
    æĭĽ
    -0.19
    aza
    -0.19
    sphere
    -0.18
    POSITIVE LOGITS
    æķijæı´
    0.38
    æ¶Īéĺ²
    0.31
    æĬ¢éĻ©
    0.29
    åľ¨çİ°åľº
    0.28
    æķijåĬ©
    0.27
    çİ°åľº
    0.27
     emergency
    0.27
    çģŃçģ«
    0.27
    åºĶæĢ¥
    0.26
    åĩºåĬ¨
    0.25
    Activations Density 0.059%

    No Known Activations