© 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. 14784
    Prev
    Next
    INDEX
    Explanations

    engine ignition timing and spark plugs

    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
    被人
    -0.21
    èijµ
    -0.20
     Rivers
    -0.20
    bane
    -0.20
    河水
    -0.20
    ocial
    -0.20
    ende
    -0.19
    让人
    -0.19
    amburger
    -0.18
    (flow
    -0.18
    POSITIVE LOGITS
    çģ«èĬ±
    0.34
    spark
    0.23
     spark
    0.22
    æłĵ
    0.22
     ExecutionContext
    0.20
    èĻº
    0.19
    çĤ¹çĩĥ
    0.18
     sparks
    0.18
    第ä¸Ģ书记
    0.18
    ç®
    0.18
    Activations Density 0.016%

    No Known Activations