© 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. 16407
    Prev
    Next
    INDEX
    Explanations

    moving or splitting code

    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
     propagation
    -0.21
     propagate
    -0.19
    term
    -0.19
    æģĥ
    -0.18
    Propagation
    -0.18
    åĨ
    -0.18
    æ¡¢
    -0.18
    (attrs
    -0.18
     getApp
    -0.18
     propag
    -0.18
    POSITIVE LOGITS
    åĪĨ离
    0.27
    社ä¼ļåĮĸ
    0.27
     decentral
    0.26
    åī¥ç¦»
    0.25
    åĪĨæķ£
    0.25
    åĪĨå¼Ģ
    0.25
     separation
    0.25
     privat
    0.24
     outsourcing
    0.23
     ÑĥÑģл
    0.23
    Activations Density 0.336%

    No Known Activations