© 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. 11630
    Prev
    Next
    INDEX
    Explanations

    "oh", "well", "alright", "no", "right"

    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
    åĵĩ
    -0.20
    é¾ļ
    -0.19
    Ầ
    -0.19
    å±ģ
    -0.18
    perf
    -0.18
     sodom
    -0.18
    ä¸Ģå¤ľ
    -0.18
    å¾ģç¨ĭ
    -0.18
    æŁĴ
    -0.18
     Kop
    -0.18
    POSITIVE LOGITS
    å¸Ŀ
    0.22
    让å®ĥ
    0.20
    硬åĮĸ
    0.20
    æħ¢
    0.19
     اÙĦجÙħÙĩÙĪر
    0.18
    æĬĬå®ĥ
    0.18
    èķĹ
    0.18
    çݩ家æľĭåıĭ
    0.18
    æĪijçľĭ
    0.18
    enburg
    0.18
    Activations Density 0.034%

    No Known Activations