© 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. 10882
    Prev
    Next
    INDEX
    Explanations

    calendar and events

    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
    åĪ°åľº
    -0.24
    士
    -0.23
    ç½ij讯
    -0.22
    flare
    -0.20
    éªĩ
    -0.20
    _ISO
    -0.20
    踣
    -0.20
    楦
    -0.20
    æ¶Īæŀģ
    -0.19
    æģ¶åĬ£
    -0.19
    POSITIVE LOGITS
    æݨåĩºçļĦ
    0.25
    åħ¨å¹´
    0.24
     season
    0.24
     calendar
    0.23
     schedule
    0.23
    åŃ£
    0.23
     selections
    0.22
    schedule
    0.22
    opening
    0.22
    next
    0.22
    Activations Density 0.021%

    No Known Activations