© 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. 12400
    Prev
    Next
    INDEX
    Explanations

    beads, residues, chains

    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
    ä¼łçľŁ
    -0.22
    ammers
    -0.21
    æĿĪ
    -0.21
    .amazonaws
    -0.20
     Speakers
    -0.20
    .readAs
    -0.19
    asty
    -0.19
    .cover
    -0.19
    aldi
    -0.19
    è°²
    -0.19
    POSITIVE LOGITS
    åĪ¶ä½ľ
    0.23
    èµĦæºIJä¼ĺåĬ¿
    0.23
    çıł
    0.23
     издели
    0.23
    è£½ä½ľ
    0.22
    åĪ¶åĵģ
    0.22
    åħĥç´ł
    0.21
     изделиÑı
    0.21
     seed
    0.21
     beads
    0.20
    Activations Density 0.011%

    No Known Activations