© 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. 15230
    Prev
    Next
    INDEX
    Explanations

    reasonable qualifier

    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
    rence
    -0.21
    ted
    -0.20
    NewLabel
    -0.19
    amp
    -0.18
    é»į
    -0.18
    æĢ§çĸ¾çĹħ
    -0.17
    ï¸ı
    -0.17
    ological
    -0.17
    licity
    -0.16
    è¯Ģ
    -0.16
    POSITIVE LOGITS
    ably
    0.27
    -sized
    0.26
     sized
    0.22
    ately
    0.20
    emente
    0.18
    hift
    0.18
    ality
    0.18
    åĵī
    0.18
    est
    0.18
    nement
    0.17
    Activations Density 0.005%

    No Known Activations