© 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. 13820
    Prev
    Next
    INDEX
    Explanations

    formal or procedural requests

    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
    æ©IJ
    -0.21
    éĴĪ
    -0.21
    ç¦ıç¥ī
    -0.20
    ç»ħ
    -0.20
    ç´¯äºĨ
    -0.19
    çĭĦ
    -0.19
    Ñģен
    -0.19
     Ñģобой
    -0.19
    _advance
    -0.19
    è·ijäºĨ
    -0.19
    POSITIVE LOGITS
    ä¹ĭä¸ĭ
    0.29
    æĮĩ导ä¸ĭ
    0.26
    é¢Ĩ导ä¸ĭ
    0.24
    å¼ķ导
    0.19
    lew
    0.19
    è¡Įäºĭ
    0.18
    âĨµ
    0.18
     apparent
    0.18
    åİŁåĪĻ
    0.17
    ä¹ĭåĬĽ
    0.17
    Activations Density 0.090%

    No Known Activations