© 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. 15033
    Prev
    Next
    INDEX
    Explanations

    highest quality, honour, common, score

    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
    åįģ足
    -0.23
    ´
    -0.20
    nier
    -0.17
    onical
    -0.15
    rine
    -0.15
    ieme
    -0.15
    .Constraint
    -0.14
     Huff
    -0.14
    راء
    -0.14
    åIJĮäºĭ
    -0.14
    POSITIVE LOGITS
    itarian
    0.25
    -order
    0.20
    OrDefault
    0.20
    mente
    0.20
    cased
    0.19
    itud
    0.19
    bred
    0.19
    ç´ļ
    0.19
    -ranked
    0.18
    -ups
    0.18
    Activations Density 0.036%

    No Known Activations