© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14931
    Prev
    Next
    INDEX
    Explanations

    election, recall, initiative, referendum

    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
    .getChildAt
    -0.22
    .getValueAt
    -0.20
    _restart
    -0.17
    -lite
    -0.17
    åĽ½åĨħå¸Ĥåľº
    -0.17
    åIJijãģį
    -0.17
    hip
    -0.17
    _shutdown
    -0.17
    charAt
    -0.17
    æĸĽ
    -0.17
    POSITIVE LOGITS
    cci
    0.21
    èĬĤ
    0.20
    ousse
    0.20
    ений
    0.20
    修补
    0.20
    VERR
    0.19
    uther
    0.19
    EFF
    0.18
    èĢĮæĪIJ
    0.18
    çĽĽå¤§
    0.18
    Activations Density 0.004%

    No Known Activations