© 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. 15129
    Prev
    Next
    INDEX
    Explanations

    .min.js / -year-old / octet-stream

    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
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.21
    åģľçĶµ
    -0.20
    æ´¥
    -0.20
    ninger
    -0.20
    ç§į
    -0.19
    åĨħè¡£
    -0.19
    _softmax
    -0.18
    许
    -0.18
    ç¼ĵ
    -0.18
    æĹłç©·
    -0.18
    POSITIVE LOGITS
    ä¸įæĩĤ
    0.23
    åĵij
    0.23
    æľ´
    0.23
    æĩµ
    0.21
    æĹłå£°
    0.21
    iec
    0.21
    ÅĽwiad
    0.20
    å¾ħ
    0.20
    Icons
    0.19
    ãģ«æĪ
    0.19
    Activations Density 0.558%

    No Known Activations