© 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. 12485
    Prev
    Next
    INDEX
    Explanations

    shaken, shake, trembling, uneasy, tremors

    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
    åıijæī¬
    -0.19
    agonal
    -0.19
    smarty
    -0.17
    imal
    -0.16
    yre
    -0.16
    rice
    -0.16
    æ¯Ķäºļ
    -0.16
    격
    -0.16
     Fighting
    -0.16
    ä¸Ģè¶Ł
    -0.16
    POSITIVE LOGITS
    ingly
    0.35
    ä¸įå®ī
    0.34
    人å¿ĥ
    0.24
    ä¸įå®ļ
    0.23
    ä¸įå·²
    0.20
    äºĨä¸Ģä¸ĭ
    0.19
    æĴ¼
    0.19
    åĬ¨æijĩ
    0.18
     lÆ°Æ¡ng
    0.18
    uar
    0.18
    Activations Density 0.045%

    No Known Activations