© 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. 17182
    Prev
    Next
    INDEX
    Explanations

    Ariel, Ari, aria

    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
    ays
    -0.21
    edList
    -0.20
    less
    -0.19
    ä¸įä½ı
    -0.18
    quet
    -0.18
    ful
    -0.17
    eds
    -0.16
    t
    -0.16
    弩
    -0.15
    edException
    -0.15
    POSITIVE LOGITS
    keit
    0.20
    å¨ħ
    0.19
    é«»
    0.18
    oyo
    0.18
    ãģ°
    0.17
    é©Ń
    0.16
    owitz
    0.16
    inces
    0.15
    è¿ĻæŶ
    0.15
    çĦ°
    0.15
    Activations Density 0.010%

    No Known Activations