© 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. 14275
    Prev
    Next
    INDEX
    Explanations

    religious sisters and nuns

    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
    åŁĻ
    -0.21
    éŃĦ
    -0.20
    èį¦
    -0.20
    以人æ°ij为
    -0.19
    æģ«
    -0.19
    ãĥįãĤ¿
    -0.19
     )↵↵↵↵↵↵↵↵
    -0.19
    æĶ¿åºľ
    -0.19
     Shaman
    -0.19
    é¦į
    -0.18
    POSITIVE LOGITS
    CloseOperation
    0.22
    ä½ľæģ¯
    0.20
    _rooms
    0.20
    inke
    0.20
    çĽijæĬ¤
    0.20
     Ones
    0.20
    _contin
    0.20
    clo
    0.19
     sisters
    0.19
    å§IJ妹
    0.19
    Activations Density 0.036%

    No Known Activations