© 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. 14488
    Prev
    Next
    INDEX
    Explanations

    degrees or pressures

    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
    _EPS
    -0.20
    å®ŀä½ĵ
    -0.20
    åºŀ大çļĦ
    -0.19
    åĽ´çĿĢ
    -0.19
    顺çĿĢ
    -0.19
    çĻ¾åIJĪ
    -0.19
    odian
    -0.19
    AXB
    -0.18
    æ²Ł
    -0.18
    wdx
    -0.18
    POSITIVE LOGITS
    æݨèįIJ
    0.26
    ä¸ĬéĻIJ
    0.24
    å©į
    0.24
     level
    0.23
    æĽ´ä½İ
    0.23
    é«ĺçļĦ
    0.22
     applied
    0.22
    å¾Īä½İ
    0.22
    çijij
    0.21
    çĴ²
    0.21
    Activations Density 0.129%

    No Known Activations