© 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. 17191
    Prev
    Next
    INDEX
    Explanations

    percentage or unit of measure

    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
    ille
    -0.20
    iph
    -0.19
    iel
    -0.19
    ç¾İ人
    -0.19
    eka
    -0.19
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.19
    æīŃ
    -0.18
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.18
    ssp
    -0.18
    igraph
    -0.17
    POSITIVE LOGITS
    èĪ¶
    0.19
    èĦ±åıij
    0.18
     incl
    0.18
    åį¯
    0.18
    даÑĩи
    0.18
    ä¸ĢçĽ´æ²¡æľī
    0.18
    ÙħÙĪÙĦ
    0.18
    èµĽåŃ£
    0.17
    个åĪ«
    0.17
     til
    0.17
    Activations Density 0.040%

    No Known Activations