© 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. 14250
    Prev
    Next
    INDEX
    Explanations

    cm thick

    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
    iker
    -0.23
    åĬłä¸Ĭ
    -0.22
    åĬłä¹ĭ
    -0.20
    inas
    -0.19
    æ¯į
    -0.19
     bare
    -0.19
    æ±Ĺæ°´
    -0.19
    åŁ´
    -0.18
    åĩº
    -0.18
    çĩĥ
    -0.18
    POSITIVE LOGITS
    宽æĿ¾
    0.21
    èľī
    0.20
    ãĤªãĥ¼ãĥĹãĥ³
    0.19
    å®ŀäºĭ
    0.19
    oss
    0.19
    åħ¬å¼Ģ课
    0.19
    çªģåĩºéĹ®é¢ĺ
    0.18
    TRAN
    0.18
    _assigned
    0.18
    áŀĦ
    0.18
    Activations Density 0.003%

    No Known Activations