© 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. 10598
    Prev
    Next
    INDEX
    Explanations

    cricket wickets for

    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
    çłģ
    -0.22
     Hatch
    -0.19
    éĢĹ
    -0.19
    aksi
    -0.18
    é¤IJæ¡Į
    -0.18
    éŁ³ç®±
    -0.18
    _NC
    -0.18
    MAP
    -0.18
    çļĦéĥ¨åĪĨ
    -0.18
    æ¶Īè´¹
    -0.18
    POSITIVE LOGITS
    液ä½ĵ
    0.22
     Hey
    0.19
    æ²ģ
    0.18
    æ¥Ķ
    0.18
    liquid
    0.18
    åı¤ä»Ĭ
    0.18
    æ¾Ħæ¸ħ
    0.18
     Witt
    0.18
    失è°ĥ
    0.18
     liquid
    0.18
    Activations Density 0.003%

    No Known Activations