© 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. 12258
    Prev
    Next
    INDEX
    Explanations

    Means Committee

    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
    åĴĮ个人
    -0.23
    åĢº
    -0.22
    亿ä¸ĩ
    -0.21
    ç¼ĸ
    -0.20
    ä»ĵä½į
    -0.18
    é¢ĺ主
    -0.18
    åħ¬è®¤
    -0.18
    åĩ½
    -0.18
    梦æĥ³
    -0.18
    pai
    -0.17
    POSITIVE LOGITS
    pte
    0.25
    egin
    0.20
    åij·
    0.19
    (reinterpret
    0.19
    æļ
    0.19
    åħ¨æµģç¨ĭ
    0.19
    _Resource
    0.18
    è¹¼
    0.17
    åıĮåIJij
    0.17
    å¦ĥ
    0.17
    Activations Density 0.005%

    No Known Activations