© 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. 16112
    Prev
    Next
    INDEX
    Explanations

    months followed by punctuation

    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
     plural
    -0.20
    ambi
    -0.20
    hare
    -0.19
    åĬ¿
    -0.19
    ack
    -0.19
    å°Ĭ
    -0.19
     REFERENCES
    -0.19
    æĶ¶
    -0.18
     purs
    -0.18
    تعÙĦÙĬ
    -0.18
    POSITIVE LOGITS
    .ss
    0.20
    两端
    0.20
    iller
    0.19
    icker
    0.18
    uct
    0.18
    ICLE
    0.18
    MEA
    0.18
    礼è²Į
    0.17
    èįīæ¡Ī
    0.17
     Wig
    0.17
    Activations Density 0.187%

    No Known Activations