© 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. 15229
    Prev
    Next
    INDEX
    Explanations

    http or media links

    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
     ent
    -0.21
    atty
    -0.19
    edy
    -0.19
    AG
    -0.18
    ****
    -0.18
    aa
    -0.18
    bow
    -0.18
     bowling
    -0.18
     bah
    -0.18
    inder
    -0.18
    POSITIVE LOGITS
    mát
    0.20
    FilterWhere
    0.20
    Ñģи
    0.19
    .generated
    0.18
    è¯Ŀé¢ĺ
    0.18
    ä¸įå¾Ĺ转载
    0.18
    纪å½ķ
    0.18
    _AdjustorThunk
    0.18
    ä¸įåħĭä¸įåıĬ
    0.17
    ãĮ¢
    0.17
    Activations Density 0.581%

    No Known Activations