© 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. 12763
    Prev
    Next
    INDEX
    Explanations

    operating system 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
    foreign
    -0.20
     conscious
    -0.19
     Vern
    -0.18
    ods
    -0.18
    neys
    -0.18
     вÑģÑİ
    -0.18
     Tory
    -0.17
    nnen
    -0.17
    éĤ£ä¸ĢåĪ»
    -0.17
    ï¸ı
    -0.17
    POSITIVE LOGITS
    çīĪæľ¬
    0.26
    æĹ¶æľŁçļĦ
    0.25
    æĹ¶æľŁ
    0.24
    çīĪ
    0.23
    èī²
    0.22
    级
    0.22
    -era
    0.22
    åĪĿæľŁ
    0.21
    涧
    0.21
     revision
    0.21
    Activations Density 0.009%

    No Known Activations