© 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. 10515
    Prev
    Next
    INDEX
    Explanations

    tumor progression and biology

    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
    ernet
    -0.18
    rup
    -0.17
    enumer
    -0.17
    ðŁı»
    -0.17
    enstein
    -0.16
    é£İåIJ¹
    -0.16
    edor
    -0.16
     Moment
    -0.16
    alloca
    -0.16
    ance
    -0.15
    POSITIVE LOGITS
    累累
    0.20
    è¸Ĭ
    0.20
    lets
    0.20
    deo
    0.19
    l
    0.19
    type
    0.18
     shrinking
    0.18
    issement
    0.17
    è¶Ĭ大
    0.17
    åŃIJéĩĮ
    0.17
    Activations Density 0.079%

    No Known Activations