© 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. 16119
    Prev
    Next
    INDEX
    Explanations

    chanting verses and phrases

    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
    æĤĦçĦ¶
    -0.23
    çĶij
    -0.23
    éļIJç§ģ
    -0.23
    æļ´é£İ
    -0.20
    une
    -0.20
    æ£ĺ
    -0.20
    åĩĮ
    -0.19
    ä¸įå¿į
    -0.19
    åĩ½
    -0.19
    çī¯
    -0.19
    POSITIVE LOGITS
    åı£åı·
    0.38
    ä¸Ģéģį
    0.33
     mantra
    0.31
     phrase
    0.31
    åĶ±
    0.30
    åĩłåı¥
    0.28
     slogan
    0.27
    chant
    0.26
    çIJħ
    0.26
     repetition
    0.26
    Activations Density 0.069%

    No Known Activations