© 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. 17217
    Prev
    Next
    INDEX
    Explanations

    mantel, coffee table, dumbwaiter, coat closet

    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
    ernes
    -0.21
    ference
    -0.18
    apult
    -0.18
    @d
    -0.18
    ienes
    -0.18
    .mesh
    -0.18
    utos
    -0.18
    rvine
    -0.17
    Celebr
    -0.17
     tatto
    -0.17
    POSITIVE LOGITS
    çĶ¸
    0.22
     безопаÑģноÑģÑĤи
    0.20
    æł·çļĦ
    0.20
    лин
    0.19
    说æ³ķ
    0.18
    odox
    0.18
    éªĹåŃIJ
    0.18
    è¥Ł
    0.18
    å¸ļ
    0.18
    ufe
    0.17
    Activations Density 0.049%

    No Known Activations