© 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. 12222
    Prev
    Next
    INDEX
    Explanations

    proper names

    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
    帻
    -0.20
    usan
    -0.19
     Elaine
    -0.19
     Rape
    -0.19
    æ·Ģ
    -0.18
    è¿Ĥ
    -0.18
    >Lorem
    -0.18
    à¸ģระà¸Ī
    -0.17
     CAS
    -0.17
    çĶ±ä¸ŃåĽ½
    -0.17
    POSITIVE LOGITS
     Getter
    0.20
    [label
    0.19
    Getter
    0.19
    UIL
    0.19
    udoku
    0.19
    åıĪ好åıĪ
    0.19
    ongsTo
    0.19
     levy
    0.18
    .station
    0.18
    zion
    0.18
    Activations Density 0.106%

    No Known Activations