© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16655
    Prev
    Next
    INDEX
    Explanations

    reality show personalities

    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
    oping
    -0.20
    ngine
    -0.20
     whims
    -0.20
     poetry
    -0.20
    elif
    -0.19
    èĢģ太太
    -0.19
     slowdown
    -0.18
     pul
    -0.18
    osen
    -0.18
     system
    -0.18
    POSITIVE LOGITS
    æĿł
    0.21
    综èīº
    0.21
    åĺī宾
    0.19
    æī©å¼ł
    0.19
    aydın
    0.19
    æī¶è´«å·¥ä½ľ
    0.18
     беÑĢем
    0.18
    èĬĤ缮ä¸Ń
    0.18
    çĶµè§Ĩ
    0.18
     allot
    0.18
    Activations Density 0.031%

    No Known Activations