© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16886
    Prev
    Next
    INDEX
    Explanations

    La followed by words/names

    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
    raft
    -0.18
    laus
    -0.18
    lah
    -0.17
    hiba
    -0.17
    nia
    -0.17
    ez
    -0.17
    ectomy
    -0.17
    ingly
    -0.16
    nis
    -0.16
    rary
    -0.16
    POSITIVE LOGITS
    igned
    0.20
    urent
    0.19
    unched
    0.19
    uded
    0.18
    amed
    0.17
    orie
    0.16
    Ùij
    0.16
    quan
    0.16
    formed
    0.16
    zier
    0.16
    Activations Density 0.029%

    No Known Activations