© 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. 14268
    Prev
    Next
    INDEX
    Explanations

    affirm, reverse, sustained

    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
    _actual
    -0.20
    ä¸ĢåĽ¢
    -0.20
    缸
    -0.19
    actual
    -0.19
    Actual
    -0.19
    è£ħ
    -0.19
     actually
    -0.18
     actual
    -0.18
    actually
    -0.18
    æīĭæĦŁ
    -0.18
    POSITIVE LOGITS
    å®ļåIJij
    0.21
    岬
    0.20
    æĥķ
    0.20
    ÑĤе
    0.20
    ä¸¥æł¼èIJ½å®ŀ
    0.19
    _flight
    0.19
    кова
    0.19
    stk
    0.18
    _NAV
    0.18
    以人æ°ij
    0.18
    Activations Density 0.043%

    No Known Activations