© 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. 13480
    Prev
    Next
    INDEX
    Explanations

    viewing and listening perspectives

    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
    åľ°ä¸Ń
    -0.23
     chambers
    -0.19
    ¯¯¯¯
    -0.19
    .trip
    -0.19
    chw
    -0.18
    cession
    -0.18
    åĿļ硬
    -0.18
    éĶ¤
    -0.18
    æľīèĥ½åĬĽ
    -0.18
    çĸıéĢļ
    -0.18
    POSITIVE LOGITS
    è§Ĥçľĭ
    0.23
     viewers
    0.23
    çľĭåĩº
    0.23
    è¿ijè§Ĩ
    0.22
     viewing
    0.22
     взглÑıд
    0.21
    çĶµè§Ĩ
    0.21
    笼罩
    0.21
    æĢ»è§īå¾Ĺ
    0.21
    åħī线
    0.21
    Activations Density 0.024%

    No Known Activations