© 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. 12883
    Prev
    Next
    INDEX
    Explanations

    incarnation of Vishnu

    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
    é¢ľ
    -0.22
    ä¸Ńéĥ¨
    -0.20
    åī¯
    -0.20
    éĢŁ
    -0.20
    éĥ¨åī¯
    -0.20
     ÑĥÑģп
    -0.20
    æĶ¶èİ·
    -0.19
     comparator
    -0.19
    åĮĸåѦ
    -0.19
    çİĩè¾¾
    -0.19
    POSITIVE LOGITS
    åĮĸ身
    0.24
    人éĹ´
    0.23
    ä¸ĸ
    0.21
    为äºĨ让
    0.21
    è·¯æ¼Ķ
    0.21
    以便
    0.20
    lico
    0.20
    ä¸ĭä¾Ĩ
    0.20
    èIJ½åľ°
    0.20
     human
    0.20
    Activations Density 0.051%

    No Known Activations