© 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. 11524
    Prev
    Next
    INDEX
    Explanations

    months of the year

    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
     ÐIJлекÑģан
    -0.20
    çĿ¨
    -0.20
    æĹłæķĮ
    -0.19
     PaÅĦstwo
    -0.19
     stead
    -0.19
     Müd
    -0.19
    èº
    -0.18
    à¸Ħà¸ĵะà¸ģรรม
    -0.18
    以åıĬ
    -0.18
    ä»ĸ们éĥ½
    -0.18
    POSITIVE LOGITS
    >NN
    0.22
    readOnly
    0.21
    (layers
    0.20
     fkk
    0.20
    hé
    0.19
    protocols
    0.19
    'gc
    0.19
    iếc
    0.19
    åİ¿åŁŁ
    0.19
    SizeMode
    0.18
    Activations Density 0.030%

    No Known Activations