© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10651
    Prev
    Next
    INDEX
    Explanations

    family relationships and personal descriptions

    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
    ãĥĬãĥ³
    -0.18
     convention
    -0.18
    utc
    -0.18
    duplicate
    -0.18
    atha
    -0.18
     Prospect
    -0.17
     Emb
    -0.17
    uv
    -0.17
    OCUS
    -0.17
     prospect
    -0.17
    POSITIVE LOGITS
    å±ŀå®ŀ
    0.21
     اÙĦخاص
    0.20
    çIJī
    0.20
    æĶĿ
    0.20
    转载请
    0.20
    inya
    0.19
     Lilly
    0.19
    æijĦ
    0.18
    reira
    0.18
    æŁľ
    0.18
    Activations Density 0.450%

    No Known Activations