© 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. 13204
    Prev
    Next
    INDEX
    Explanations

    Top 10

    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
    çļĦå°±æĺ¯
    -0.20
    åīįæīĢ
    -0.19
    åħ¶ä¸Ń
    -0.19
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.19
    MA
    -0.18
    çĶŁäº§æĢ»
    -0.18
    HEL
    -0.18
    åĮĻ
    -0.17
    ald
    -0.17
    è¯¥æł¡
    -0.17
    POSITIVE LOGITS
    ä¿©
    0.21
    ignment
    0.21
    两åı¥
    0.21
    _specs
    0.19
    äu
    0.19
    'clock
    0.18
    仨
    0.18
    }->{
    0.17
    asive
    0.17
    quence
    0.17
    Activations Density 0.025%

    No Known Activations