© 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. 11938
    Prev
    Next
    INDEX
    Explanations

    actuators, servos, motors, cylinders

    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
    shed
    -0.23
    nad
    -0.21
    .filename
    -0.21
    antium
    -0.21
     Lyons
    -0.20
    matchCondition
    -0.19
    .FileName
    -0.19
    .gpu
    -0.19
    izr
    -0.19
    峡
    -0.19
    POSITIVE LOGITS
    带åĬ¨
    0.26
    åĬ¨ä½ľ
    0.26
     actions
    0.24
    æľºæŀĦ
    0.24
     action
    0.24
    æĪ¿
    0.23
     precision
    0.22
     motion
    0.22
    è¡Įç¨ĭ
    0.22
    forth
    0.22
    Activations Density 0.082%

    No Known Activations