© 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. 15788
    Prev
    Next
    INDEX
    Explanations

    closing punctuation, followed by text

    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
    imo
    -0.22
    iat
    -0.21
    ipl
    -0.19
    天åłĤ
    -0.18
     Pell
    -0.18
    es
    -0.17
    ively
    -0.17
    ä¸į让
    -0.17
    iele
    -0.17
    esch
    -0.16
    POSITIVE LOGITS
    楼ä¸Ĭ
    0.18
    åħ±åĪĽ
    0.17
    媪
    0.17
    黳
    0.16
    ãĤĥ
    0.16
    nbsp
    0.16
    åĬ¡å®ŀ
    0.16
    зов
    0.16
    è¹ij
    0.16
    annies
    0.16
    Activations Density 0.077%

    No Known Activations