© 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. 16123
    Prev
    Next
    INDEX
    Explanations

    psychic, oracle, prophet, spiritual

    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
    çĿ¦
    -0.21
    itled
    -0.20
    æ´ģ
    -0.20
    ç¹ģ
    -0.20
    å·¥ç¨ĭè´¨éĩı
    -0.19
    太大
    -0.19
    .toolbar
    -0.19
     Choir
    -0.19
    ä¸īçĻ¾
    -0.18
    ahl
    -0.18
    POSITIVE LOGITS
    é¢Ħæµĭ
    0.39
    é¢Ħè¨Ģ
    0.36
     predicting
    0.28
    ðŁĶ®
    0.28
     prediction
    0.26
     progn
    0.25
    é¢ĦæĬ¥
    0.24
     prophecy
    0.24
     predicts
    0.24
    åįľ
    0.24
    Activations Density 0.019%

    No Known Activations