© 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. 11873
    Prev
    Next
    INDEX
    Explanations

    levels of

    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
    cke
    -0.20
    ä¼ģä¸ļæıIJä¾Ľ
    -0.20
    iets
    -0.20
    cott
    -0.20
    cken
    -0.19
    .fb
    -0.19
    vest
    -0.19
    åIJ§
    -0.19
    åŃ£åIJİ
    -0.19
    ä¹IJåĽŃ
    -0.18
    POSITIVE LOGITS
    éĢŀ
    0.24
    åı¯è§Ĥ
    0.24
    两项
    0.23
    è¡¡éĩı
    0.23
    çŃīå¤ļ项
    0.22
    åIJĮæŶè¿ĺ
    0.22
    ä¸įä»ħå¦ĤæѤ
    0.20
    ä¸ī项
    0.20
     NSLayoutConstraint
    0.20
    åIJĮæĹ¶ä¹Ł
    0.19
    Activations Density 0.095%

    No Known Activations