© 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. 14054
    Prev
    Next
    INDEX
    Explanations

    months and US states

    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
    erah
    -0.20
    Parm
    -0.17
    rides
    -0.17
    pdb
    -0.16
    .inc
    -0.16
    >>>>>>>>
    -0.16
    inky
    -0.15
    liga
    -0.15
    /-
    -0.15
    çīµ
    -0.15
    POSITIVE LOGITS
    oux
    0.19
    带走
    0.19
    çľ¼çķĮ
    0.17
    çľĭ书
    0.17
    umas
    0.17
    ToFit
    0.16
    wards
    0.16
    apon
    0.16
    /of
    0.16
    秽
    0.16
    Activations Density 0.102%

    No Known Activations