© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14885
    Prev
    Next
    INDEX
    Explanations

    abduct, abduction

    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
    mony
    -0.20
    æľīä»»ä½ķ
    -0.18
     Äijấu
    -0.18
    liness
    -0.17
    å·²ä¹ħçļĦ
    -0.17
    å¾Ĺä½ı
    -0.17
    veau
    -0.17
    APTER
    -0.17
    DSA
    -0.17
    mü
    -0.17
    POSITIVE LOGITS
    phinx
    0.17
    ãĥķãĤ©ãĥ¼
    0.17
    ively
    0.17
    éĵ¡
    0.17
    女çĶŁ
    0.17
    hem
    0.17
     nghiá»ĩp
    0.17
    éħļ
    0.17
    åĪĥ
    0.16
    åĿĤ
    0.16
    Activations Density 0.001%

    No Known Activations