© 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. 10780
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
     Webseite
    -0.19
    误
    -0.18
    pyx
    -0.18
    qa
    -0.18
    .blank
    -0.18
    lington
    -0.18
    ertest
    -0.18
    arten
    -0.17
     Bour
    -0.17
    omm
    -0.17
    POSITIVE LOGITS
    çī¹æľīçļĦ
    0.28
     feature
    0.24
    èĩªå¸¦
    0.24
    åľ¨è¿Ļæĸ¹éĿ¢
    0.23
    çļĦä¸Ģ大
    0.23
    åIJ¯çĶ¨
    0.21
    以åIJİ
    0.21
    feature
    0.21
    Features
    0.20
    åıĬ以ä¸Ĭ
    0.20
    Activations Density 0.289%

    No Known Activations