© 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. 13708
    Prev
    Next
    INDEX
    Explanations

    coercion, extortion, intimidation

    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
    vsp
    -0.21
    ä»ħ代表
    -0.21
    yssey
    -0.19
    ãģ¤ãģı
    -0.18
    ä»ĸæĺ¯ä¸Ģ个
    -0.18
    ronic
    -0.18
    èĮ¨
    -0.17
    nip
    -0.17
    _shift
    -0.17
    æĺ±
    -0.17
    POSITIVE LOGITS
    ingly
    0.22
    uring
    0.21
     leverage
    0.20
    ä½ıäºĨ
    0.18
    èĥ´
    0.18
    迫使
    0.17
    ä¸įæĪIJ
    0.17
    åĭĴ
    0.17
    æľīåĬĽ
    0.17
    enberg
    0.17
    Activations Density 0.006%

    No Known Activations