© 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. 16743
    Prev
    Next
    INDEX
    Explanations

    Tata, ICICI, Miguel, Bank, Pharma

    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
    roph
    -0.23
    Occ
    -0.21
    dir
    -0.21
    form
    -0.20
    Form
    -0.20
    çŃIJ
    -0.20
    è®Ń
    -0.20
    jur
    -0.19
    Dis
    -0.19
    Ghost
    -0.19
    POSITIVE LOGITS
    éĽĨåĽ¢
    0.23
    ä¸ĩäºĭ
    0.23
    çĥŃ度
    0.21
    çĪ¶åŃIJ
    0.21
    å®ŀä¸ļ
    0.21
    èĤ¡ä»·
    0.20
     Ruiz
    0.20
    agini
    0.20
    åĪĽå§ĭ
    0.20
    ä¹ĭæĺŁ
    0.19
    Activations Density 0.050%

    No Known Activations