© 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. 16305
    Prev
    Next
    INDEX
    Explanations

    Social Security or security-related actions

    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
    å»ĵ
    -0.19
     Partition
    -0.18
    OfClass
    -0.18
    .Members
    -0.18
     Kol
    -0.18
     gm
    -0.17
    ulan
    -0.17
    éĺ²å®Ī
    -0.17
    achten
    -0.17
    LocalStorage
    -0.17
    POSITIVE LOGITS
    ç½ijéĢļ
    0.22
    ÑĢÑĥж
    0.21
    丧
    0.20
    bourg
    0.18
    roud
    0.18
    rab
    0.17
     worker
    0.17
    工伤
    0.17
    åijĺ
    0.17
    å±Ģåī¯å±Ģéķ¿
    0.17
    Activations Density 0.002%

    No Known Activations