© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17175
    Prev
    Next
    INDEX
    Explanations

    date and metadata

    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
    Negative Logits
    éĥ½éĿŀ常
    -0.20
    éĶµ
    -0.19
    éľ¹
    -0.18
    åĨĻçĿĢ
    -0.17
    ardi
    -0.17
    ä»Ģä¹Īåij¢
    -0.17
    èĩ³ä¸Ĭ
    -0.17
    sing
    -0.17
    upon
    -0.17
    atur
    -0.17
    POSITIVE LOGITS
    erate
    0.18
    æŶåĪ»
    0.18
    æľīä¸Ģç§į
    0.18
     Views
    0.17
    pcl
    0.17
    unist
    0.17
    á´´
    0.17
     Fluent
    0.17
    çĶ»éĿ¢
    0.16
    çī¹æ´¾
    0.16
    Activations Density 0.081%

    No Known Activations