© 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. 14165
    Prev
    Next
    INDEX
    Explanations

    contributed by

    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
    -night
    -0.20
    Bow
    -0.19
    å·®
    -0.19
    å®īæİĴ
    -0.19
    bow
    -0.18
     cont
    -0.18
    ç»ĵ
    -0.18
    uchs
    -0.18
    pirit
    -0.18
    èī°
    -0.18
    POSITIVE LOGITS
    è´¡çĮ®
    0.27
    è¡·
    0.27
    contrib
    0.24
    å¾ģéĽĨ
    0.24
    -contrib
    0.23
    åıĤèµĽ
    0.23
     contributions
    0.23
    åĮ¿åIJį
    0.22
    æĿ¥èĩª
    0.21
    åıįé¦Ī
    0.21
    Activations Density 0.032%

    No Known Activations