© 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. 14599
    Prev
    Next
    INDEX
    Explanations

    reviewers and names

    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
    uco
    -0.20
    ç´¢èµĶ
    -0.20
    翳
    -0.20
    วà¸Ķ
    -0.19
    .collections
    -0.19
    _claim
    -0.19
    æĶ¶å½ķ
    -0.19
    ître
    -0.19
    ç¯Ŀ
    -0.18
    ICODE
    -0.18
    POSITIVE LOGITS
    äºĶåħŃ
    0.24
    æ³¢
    0.22
    æĢ¥
    0.20
    åĤ¬
    0.20
    åĬłå¿«
    0.18
    æķ¦
    0.18
    å¿«
    0.18
    çŁ¥
    0.18
    PC
    0.18
    忧
    0.18
    Activations Density 0.119%

    No Known Activations