© 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. 16296
    Prev
    Next
    INDEX
    Explanations

    scientific journal titles

    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
    åijĽ
    -0.22
    å¼Ģåıij建设
    -0.22
    ocks
    -0.21
    oref
    -0.20
    åĩºå±Ģ
    -0.20
    _locals
    -0.19
    çĻ¾åĪĨä¹ĭ
    -0.19
    à¹ģà¸Ĺ
    -0.18
    outu
    -0.18
    éĽĨ
    -0.18
    POSITIVE LOGITS
    éĺ´
    0.20
    fil
    0.19
    principal
    0.19
     teen
    0.19
     susp
    0.19
    .getComponent
    0.19
    teen
    0.18
    ĮĢ
    0.18
     Zw
    0.17
    深度
    0.17
    Activations Density 0.017%

    No Known Activations