© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15252
    Prev
    Next
    INDEX
    Explanations

    butterflies and moths

    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
    çĵĺ
    -0.21
     Desk
    -0.18
    ึ
    -0.18
    éŁ³é¢ij
    -0.18
    æ»ļçIJĥ
    -0.18
    éŁ³åĵį
    -0.18
    æĮĸ
    -0.18
    _CHUNK
    -0.18
     Gear
    -0.18
     gear
    -0.17
    POSITIVE LOGITS
    ç¿ħèĨĢ
    0.27
     butterflies
    0.24
     flutter
    0.24
    èĿ´èĿ¶
    0.23
    æīij
    0.23
     butterfly
    0.22
    é£ŀç¿Ķ
    0.22
    é²ľèī³
    0.21
    åĩłå¼ł
    0.20
    è¹ģ
    0.20
    Activations Density 0.052%

    No Known Activations