© 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. 15974
    Prev
    Next
    INDEX
    Explanations

    what's at stake

    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
    oger
    -0.21
    足迹
    -0.20
    freq
    -0.19
    ä¿Ŀ湿
    -0.18
    åģ¶
    -0.18
    доб
    -0.18
    é¢Ĩè·ij
    -0.17
    åĹľ
    -0.17
    读åIJİ
    -0.17
    æŃ·
    -0.17
    POSITIVE LOGITS
    åħ³ä¹İ
    0.29
    çĶŁæŃ»
    0.29
    æĪIJè´¥
    0.29
    äºĭåħ³
    0.28
    åĪ©çĽĬ
    0.26
    羣åģĩ
    0.24
    åĨ³å®ļ
    0.23
    æĢ§åij½
    0.23
    åīįéĢĶ
    0.23
     decides
    0.21
    Activations Density 0.028%

    No Known Activations