© 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. 14605
    Prev
    Next
    INDEX
    Explanations

    things ending in a suffix or adverb

    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
    èij©
    -0.21
     yourselves
    -0.20
    å®ĿçŁ³
    -0.19
    Mess
    -0.18
    Sugar
    -0.18
    grave
    -0.18
    æĬĵç´§
    -0.18
    ridged
    -0.17
    antor
    -0.17
    åŃIJå¼Ł
    -0.17
    POSITIVE LOGITS
    ç±³å°Ķ
    0.23
    StateManager
    0.20
    èĬ¸
    0.19
    æĤĶ
    0.19
    æīĵçĿĢ
    0.19
    çļĦä¼Łå¤§
    0.19
    ä¸ĩ亿
    0.18
    害
    0.18
    ç»Īæŀģ
    0.18
     Bud
    0.18
    Activations Density 0.171%

    No Known Activations