© 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. 13887
    Prev
    Next
    INDEX
    Explanations

    personally identifiable information

    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
    ç½
    -0.21
    æł¹æį®èĩªå·±
    -0.20
    çIJĥ
    -0.20
    styleType
    -0.20
    åIJĪéĩij
    -0.19
     اÙĦÙħجÙĦس
    -0.19
    åIJĮ缣
    -0.19
    ParallelGroup
    -0.18
    ç½¢äºĨ
    -0.18
    åĢĻ
    -0.18
    POSITIVE LOGITS
    个ä½ĵ
    0.28
     individual
    0.25
     personally
    0.25
    individual
    0.23
    /dat
    0.23
    _individual
    0.22
     cre
    0.22
    ID
    0.21
    Individual
    0.21
     Individual
    0.21
    Activations Density 0.014%

    No Known Activations