© 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. 16694
    Prev
    Next
    INDEX
    Explanations

    exception handling

    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
     bist
    -0.20
    形容
    -0.20
    人éĢī
    -0.20
    allet
    -0.19
    /part
    -0.19
    .Constants
    -0.19
    两岸
    -0.19
    ợ
    -0.18
    ammers
    -0.18
    Pale
    -0.18
    POSITIVE LOGITS
    (Throwable
    0.32
    (SQLException
    0.28
    (Exception
    0.26
     thrown
    0.25
    thrown
    0.25
    æįķæįī
    0.25
     catcher
    0.25
     throwable
    0.25
    Occurred
    0.24
     Caught
    0.24
    Activations Density 0.336%

    No Known Activations