© 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. 10560
    Prev
    Next
    INDEX
    Explanations

    earlier this

    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
    smith
    -0.20
    ìį¨
    -0.18
    mith
    -0.18
    istic
    -0.17
    manship
    -0.17
    è¶³å¤Ł
    -0.17
    scape
    -0.17
    tre
    -0.17
    aroo
    -0.17
    åħį责声æĺİ
    -0.17
    POSITIVE LOGITS
    _THAN
    0.29
    _than
    0.28
    -than
    0.28
    Than
    0.23
     than
    0.21
    than
    0.21
     ÑĢанее
    0.20
    说è¿ĩ
    0.20
    зн
    0.18
    chant
    0.17
    Activations Density 0.009%

    No Known Activations