© 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. 16529
    Prev
    Next
    INDEX
    Explanations

    most [adjective]

    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
    åĢij
    -0.19
    çļĦæĪIJéķ¿
    -0.19
    itty
    -0.18
    æľīè¶³å¤ŁçļĦ
    -0.18
    éĥ½åĸľæ¬¢
    -0.18
    们çļĦ
    -0.18
    æľīæĿ¡ä»¶çļĦ
    -0.18
    æľīå¾Ī大çļĦ
    -0.17
    çļĦå¢ŀéķ¿
    -0.17
    çļĦèī¯å¥½
    -0.17
    POSITIVE LOGITS
    -ever
    0.20
    eker
    0.20
    ever
    0.19
    è¿·
    0.18
    akit
    0.18
     thing
    0.18
    ness
    0.18
    çĪ±ä½ł
    0.18
    thing
    0.18
    ech
    0.17
    Activations Density 0.056%

    No Known Activations