© 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. 16814
    Prev
    Next
    INDEX
    Explanations

    creamy texture

    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
    çģ¯ç¬¼
    -0.20
    è´¸
    -0.20
    minster
    -0.19
    æĨ©
    -0.19
    å·¥ä½ľä¼ļè®®
    -0.19
    åĴĮåľ°åĮº
    -0.18
    mite
    -0.18
    è¤Ĭ
    -0.18
    èĮ¬
    -0.18
    gings
    -0.18
    POSITIVE LOGITS
     smooth
    0.19
    æµģçķħ
    0.19
     finish
    0.19
    hä
    0.18
    ullen
    0.17
    wed
    0.17
    áĢĿ
    0.17
    ãĥĥãĤ·ãĥ¥
    0.17
     segue
    0.17
     crunch
    0.17
    Activations Density 0.003%

    No Known Activations