© 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. 14452
    Prev
    Next
    INDEX
    Explanations

    greeting card

    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
    è¿Ļéĥ¨
    -0.20
    鬣
    -0.20
    _hal
    -0.20
    å¬ĸ
    -0.20
    éĶħ
    -0.19
    ãĥıãĥ³
    -0.19
    forums
    -0.19
     Quentin
    -0.19
    æºĥ
    -0.18
    顽强
    -0.18
    POSITIVE LOGITS
    大æĸ¹
    0.24
     cards
    0.23
    åį¡çīĩ
    0.22
     card
    0.22
    _sent
    0.21
    éĢģåĩº
    0.20
    æİĸ
    0.20
     Harbor
    0.20
    reuse
    0.20
    è´º
    0.20
    Activations Density 0.009%

    No Known Activations