© 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. 11067
    Prev
    Next
    INDEX
    Explanations

    puzzle clues

    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
     Ranch
    -0.20
    .addAction
    -0.19
    OrDefault
    -0.19
     videos
    -0.19
     privat
    -0.18
     McMaster
    -0.18
    arb
    -0.18
    ä½ķæŶ
    -0.18
    éģĤ
    -0.18
    é¦Ħ
    -0.17
    POSITIVE LOGITS
     crossword
    0.32
    è°ľ
    0.28
    线索
    0.28
     puzzle
    0.24
    å¡«
    0.23
    è¯į
    0.23
     clues
    0.22
    ç½®æį¢
    0.22
    uzzle
    0.22
     clue
    0.21
    Activations Density 0.013%

    No Known Activations