© 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. 11114
    Prev
    Next
    INDEX
    Explanations

    phone numbers and postal codes

    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
    tent
    -0.21
    ihad
    -0.20
    ä»İ
    -0.20
    为åħ¶
    -0.19
    åłµ
    -0.19
    éĩį
    -0.18
    èħIJ
    -0.18
    æĸ°åĬ¨èĥ½
    -0.17
    大å¹ħ
    -0.17
    éĤ£
    -0.17
    POSITIVE LOGITS
    imony
    0.23
    .handleClick
    0.19
    æµ®
    0.19
    -null
    0.18
    åĬ³åĬ¡
    0.17
     cucumber
    0.17
    æģ½
    0.17
    UNC
    0.17
    人åĵ¡
    0.17
    ansson
    0.17
    Activations Density 0.010%

    No Known Activations