© 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. 16336
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    æĺĢ
    -0.19
    EndInit
    -0.19
     face
    -0.18
     mug
    -0.18
    åĬłä¹ĭ
    -0.18
    .bunifuFlatButton
    -0.18
     plane
    -0.18
    ä½Ĩä»į
    -0.17
    æ³Ĭ
    -0.17
    éĥħ
    -0.17
    POSITIVE LOGITS
    å¦Ĥä½ķçľĭå¾ħ
    0.30
    为ä»Ģä¹Īä¼ļ
    0.30
    为ä½ķ
    0.29
    ä»Ģä¹Īæĺ¯
    0.27
    为ä»Ģä¹Ī
    0.27
    为ä»Ģä¹Īè¦ģ
    0.24
    ãģªãģľ
    0.24
    naire
    0.23
    æĢİä¹Īçľĭ
    0.23
    为ä»Ģä¹Īä¸į
    0.23
    Activations Density 0.323%

    No Known Activations