© 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. 17286
    Prev
    Next
    INDEX
    Explanations

    study of data

    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
    PropertyParams
    -0.35
    Cumhur
    -0.34
     désorm
    -0.33
     erotisk
    -0.30
    âīĤ
    -0.30
    è¿«ä¸įåıĬ
    -0.30
     пÑĢиÑıÑĤн
    -0.30
     salopes
    -0.29
     limburg
    -0.29
     amatør
    -0.29
    POSITIVE LOGITS
    èĸ¤
    0.22
    item
    0.22
     were
    0.21
    çłĶ究人åijĺ
    0.21
    d
    0.21
    缸èģļ
    0.21
     hadde
    0.21
    éĤ£æ®µ
    0.21
     pasta
    0.21
    were
    0.21
    Activations Density 0.229%

    No Known Activations