© 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. 16295
    Prev
    Next
    INDEX
    Explanations

    particular file

    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
    ths
    -0.20
    ово
    -0.19
    uality
    -0.19
     ìķĦëĭĮ
    -0.18
    .getStatus
    -0.18
    å¤ĸåĽ´
    -0.18
    家åĽŃ
    -0.18
    stown
    -0.18
    ritch
    -0.18
    çłĶ究表æĺİ
    -0.18
    POSITIVE LOGITS
    èĻı
    0.19
     heaps
    0.18
    ioc
    0.18
    èµİ
    0.18
    å¹´åĨħ
    0.18
    ä¹Łå¸ĮæľĽ
    0.18
    big
    0.18
     catast
    0.18
     redeemed
    0.17
    éĢģåĪ°
    0.17
    Activations Density 0.001%

    No Known Activations