© 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. 11507
    Prev
    Next
    INDEX
    Explanations

    guidance and support

    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
    ActionTypes
    -0.20
    agar
    -0.20
    ä¸ĩ象
    -0.19
    CardBody
    -0.19
    åħĢ
    -0.19
    alte
    -0.18
    -0.18
    ç©·
    -0.18
     XO
    -0.18
    ä»ħ代表
    -0.17
    POSITIVE LOGITS
    æĮĩ导
    0.28
     guidance
    0.26
    æĮĩå°İ
    0.23
    æĦīå¿«
    0.21
    åĴĮæĶ¯æĮģ
    0.20
    æĮĩçĤ¹
    0.20
    å¼Ģå±ķ
    0.20
    å¿ħè¦ģçļĦ
    0.20
    å¤ļç§įå½¢å¼ı
    0.20
    .direction
    0.20
    Activations Density 0.042%

    No Known Activations