© 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. 16053
    Prev
    Next
    INDEX
    Explanations

    current page or state

    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
    ç¿ħ
    -0.22
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.22
    åIJĦåľ°
    -0.20
    类似çļĦ
    -0.19
    æİĸ
    -0.19
    æĽ¿
    -0.18
     initialValues
    -0.18
    ä¸įéĶĪ
    -0.18
    .birth
    -0.18
    Keith
    -0.18
    POSITIVE LOGITS
    æŃ£åľ¨è¿Ľè¡Į
    0.28
    æŃ£åľ¨
    0.28
    æѤåĪ»
    0.25
    å½ĵæŶ
    0.23
     task
    0.21
    æѤæŶ
    0.21
     situation
    0.20
    енно
    0.19
     surroundings
    0.19
    cer
    0.18
    Activations Density 0.157%

    No Known Activations