© 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. 11674
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    æ°¤
    -0.18
    angs
    -0.18
    atra
    -0.17
    stars
    -0.17
    _UNIX
    -0.17
    æ°°
    -0.17
    .toCharArray
    -0.17
    çģµæĦŁ
    -0.17
    æĺ¥é£İ
    -0.17
     Marino
    -0.17
    POSITIVE LOGITS
    uid
    0.20
    pac
    0.19
    eed
    0.19
    ettel
    0.18
    è°
    0.18
     Apost
    0.17
    eshire
    0.17
    管çIJĨåijĺ
    0.17
    ilio
    0.17
     Dropbox
    0.16
    Activations Density 0.001%

    No Known Activations