© 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. 12858
    Prev
    Next
    INDEX
    Explanations

    Fast, Slow, Func

    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
     Coupons
    -0.19
    PIP
    -0.19
    éĻª
    -0.18
    å¤ĸåĽ½
    -0.18
    Callbacks
    -0.18
    _dot
    -0.18
    .dot
    -0.18
    fillable
    -0.17
    å¤ĸåĽ½äºº
    -0.17
     SDS
    -0.17
    POSITIVE LOGITS
    olie
    0.21
    oldt
    0.20
    çĿ½
    0.19
    çļĦçĪ±æĥħ
    0.19
    éĤ£éº¼
    0.19
    è°¢éĤĢ
    0.18
    è¯Ľ
    0.18
    ãģ¨ãģĵãĤįãģ§
    0.18
     lic
    0.18
    èĦ¸èī²
    0.18
    Activations Density 0.031%

    No Known Activations