© 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. 10689
    Prev
    Next
    INDEX
    Explanations

    tense and tension

    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
    Not in Any Lists

    No Comments

    Negative Logits
    à¹Į
    -0.25
    ization
    -0.21
    shire
    -0.21
    isation
    -0.20
    lah
    -0.19
    ised
    -0.19
    ized
    -0.19
    ãģĦãģ¾ãģĻ
    -0.18
    tek
    -0.18
    ãģĦãĤĭ
    -0.17
    POSITIVE LOGITS
    ened
    0.22
    ãģĩ
    0.20
    ëį°
    0.19
    NESS
    0.19
    lessly
    0.18
    ingly
    0.18
     Indy
    0.17
    лив
    0.17
    eners
    0.17
    ening
    0.17
    Activations Density 0.022%

    No Known Activations