© 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. 10365
    Prev
    Next
    INDEX
    Explanations

    prospective

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.18
    æĸ¯é¡¿
    -0.18
    aker
    -0.17
    uth
    -0.17
    ستاÙĨ
    -0.17
    æѤåĪ»
    -0.16
    rock
    -0.16
     pháºŃn
    -0.15
    ProductName
    -0.15
    éĵĽ
    -0.15
    POSITIVE LOGITS
    ively
    0.30
    ally
    0.23
    ors
    0.21
    åĿŀ
    0.20
    ivity
    0.19
    ually
    0.18
    ä¸įä½³
    0.17
    ality
    0.17
    eur
    0.16
    ivamente
    0.16
    Activations Density 0.024%

    No Known Activations