© 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. 11440
    Prev
    Next
    INDEX
    Explanations

    internet connection or failure

    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
    çĦ¶æĺ¯
    -0.21
    urtle
    -0.17
    erness
    -0.17
    éĴ
    -0.16
    ulous
    -0.16
    libraries
    -0.16
    lah
    -0.16
    åħ¶ä¸Ńä¸Ģ个
    -0.16
    ÑģÑı
    -0.16
    许å¤ļ
    -0.15
    POSITIVE LOGITS
    lessly
    0.20
    ocus
    0.19
    ãĤº
    0.18
    less
    0.18
    egan
    0.18
    GES
    0.18
    cco
    0.18
     Chall
    0.18
    atics
    0.17
    UFF
    0.17
    Activations Density 0.023%

    No Known Activations