© 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. 15579
    Prev
    Next
    INDEX
    Explanations

    targeting specific audiences

    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
    å®īæİĴ
    -0.22
    ç»Ħç»ĩé¢Ĩ导
    -0.19
    æĺ¥å¤©
    -0.18
    梽
    -0.18
    æĪij对
    -0.18
    沿çĿĢ
    -0.17
    åѤç«ĭ
    -0.17
    DOMNode
    -0.17
    #line
    -0.17
    缤
    -0.17
    POSITIVE LOGITS
    åıĹä¼Ĺ
    0.35
     audience
    0.32
     audiences
    0.28
    è§Ĥä¼Ĺ
    0.28
    读èĢħ
    0.27
    -target
    0.24
     readers
    0.24
    å®ļä½į
    0.24
     targets
    0.24
     viewers
    0.23
    Activations Density 0.038%

    No Known Activations