© 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. 15082
    Prev
    Next
    INDEX
    Explanations

    historian and archives

    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
    ebra
    -0.18
    ichern
    -0.18
    _resolve
    -0.17
    å¥ĭæĸĹ
    -0.17
    è¿ľæ´ĭ
    -0.17
    лÑı
    -0.17
    ted
    -0.17
    èī¯å¥½
    -0.16
    èĦijåŃIJ
    -0.16
     Wit
    -0.16
    POSITIVE LOGITS
    å·¥ä½ľäººåijĺ
    0.24
    室
    0.23
    åĵ¡
    0.23
    åijĺ
    0.22
    yard
    0.21
    å·¥ä½ľèĢħ
    0.21
    yer
    0.20
    craft
    0.20
    ACY
    0.19
    ute
    0.18
    Activations Density 0.006%

    No Known Activations