© 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. 16510
    Prev
    Next
    INDEX
    Explanations

    relative motion or movement

    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
    ç¨į
    -0.20
     parach
    -0.20
    ç¿İ
    -0.20
     vest
    -0.20
    æ»´
    -0.20
     calor
    -0.19
    ihad
    -0.19
    éĨ¯
    -0.19
    ç¿Ĭ
    -0.19
    ä¸Ģçľ¼
    -0.19
    POSITIVE LOGITS
    è¿IJåĬ¨
    0.27
     motion
    0.27
     движениÑı
    0.27
    带åĬ¨
    0.27
     movement
    0.26
     relative
    0.25
    motion
    0.24
    åĬ¨ä½ľ
    0.23
     movimiento
    0.23
    -relative
    0.22
    Activations Density 0.260%

    No Known Activations