© 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. 17107
    Prev
    Next
    INDEX
    Explanations

    response rate or remission

    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
    AGER
    -0.20
    ложениÑı
    -0.20
    egrity
    -0.19
    ä»ĩæģ¨
    -0.19
    é£İæ°Ķ
    -0.18
    åį±å®³
    -0.18
    æĸ¹åľĨ
    -0.18
     pand
    -0.18
    è¡ħ
    -0.18
    çĭŀ
    -0.18
    POSITIVE LOGITS
    æľŁåĨħ
    0.23
    æľŁ
    0.23
     flatt
    0.21
    满æĦıçļĦ
    0.20
    ç»ĵå±Ģ
    0.20
    è§ģæķĪ
    0.20
    åĿª
    0.19
    umper
    0.19
    Flat
    0.19
    çĹħæĥħ
    0.19
    Activations Density 0.183%

    No Known Activations