© 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. 10425
    Prev
    Next
    INDEX
    Explanations

    long exposure photography

    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
    å
    -0.23
    缴è¾ĸ
    -0.22
    ç³Ļ
    -0.20
     Pieces
    -0.19
    .dispatch
    -0.19
    åĬ£
    -0.19
     Crest
    -0.19
    chi
    -0.18
    SupportedContent
    -0.18
    _ZONE
    -0.18
    POSITIVE LOGITS
    æ·±å¤ľ
    0.24
    累积
    0.23
    æŶéĹ´ä¸º
    0.23
     вÑĢемени
    0.23
    åħīéĺ´
    0.22
    æŶéĹ´
    0.22
    æŶéĹ´åĨħ
    0.21
    å¤ľ
    0.21
    积累
    0.21
    æŶéĹ´æ®µ
    0.20
    Activations Density 0.017%

    No Known Activations